© 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. 8904
    Prev
    Next
    INDEX
    Explanations

    Data range checks (ASIL A)

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

    The neuron is picking out content‐bearing words (nouns, verbs, adjectives, etc.) rather than common function words.

    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
    দিনী
    0.78
    8
    0.77
    9
    0.76
    ﺒ
    0.75
    3
    0.75
    4
    0.73
    7
    0.72
    2
    0.68
     Krank
    0.67
     энциклопедия
    0.67
    POSITIVE LOGITS
     végétation
    0.84
     vér
    0.78
    Surname
    0.77
    urilor
    0.77
    رى
    0.75
    يز
    0.75
    वर्क
    0.74
    ala
    0.72
    يت
    0.71
    avelmente
    0.71
    Activations Density 0.001%

    No Known Activations