© 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. 14506
    Prev
    Next
    INDEX
    Explanations

    instruction endpoint sentence challenge feeling tool you

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

    The neuron consistently lights up on content‐bearing nouns—key topic words that carry the main subjects or objects in the text.

    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
    ের
    1.01
    উ
    0.78
    ্যাক
    0.74
    EP
    0.73
    Ꭳ
    0.72
    აქ
    0.72
    ита
    0.71
    анта
    0.69
    雹
    0.68
    र्ड
    0.68
    POSITIVE LOGITS
    们
    1.66
    們
    1.66
    们的
    1.63
    들에
    1.49
    larla
    1.48
    들
    1.46
    sthe
    1.45
    들은
    1.43
    ‌های
    1.41
    들도
    1.38
    Activations Density 2.170%

    No Known Activations