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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6148
    Prev
    Next
    INDEX
    Explanations

    concepts related to associations

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

    The neuron specifically detects numeric tokens representing decimal or floating-point numbers.

    oai_token-act-pair · o4-miniTriggered 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
     sakit
    0.88
     بیمار
    0.80
     ş
    0.80
     rigid
    0.79
     wojewód
    0.77
     hastalık
    0.76
     scum
    0.75
    argout
    0.75
     benzyl
    0.74
     بگیر
    0.74
    POSITIVE LOGITS
    Texture
    0.77
    ام
    0.73
    PROVID
    0.72
    聽
    0.71
    تس
    0.70
    ContentType
    0.70
     обуча
    0.70
    ان
    0.69
    SHA
    0.69
     Danielle
    0.69
    Activations Density 0.001%

    No Known Activations