© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13518
    Prev
    Next
    INDEX
    Explanations

    between theory and practice

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates almost exclusively on tokens representing floating‐point numbers (i.e. numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    whitespace characters, particularly line breaks and paragraph separators in formatted text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    words containing internal punctuation, especially apostrophes in contractions/possessives and hyphens in compound forms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一是
    0.95
    ங்கிணை
    0.80
    先日
    0.78
    𝑧
    0.77
    ব
    0.76
     sanitaria
    0.75
    ⿸
    0.75
     préciser
    0.74
    门口
    0.73
     calda
    0.73
    POSITIVE LOGITS
    Tenemos
    0.69
     хотелось
    0.68
     Islands
    0.64
     চাই
    0.64
     वांछ
    0.64
    зей
    0.63
     أنها
    0.63
     крепо
    0.63
     والصلاه
    0.63
    קים
    0.62
    Activations Density 0.001%

    No Known Activations