© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7761
    Prev
    Next
    INDEX
    Explanations

    nor, and

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

    cannot / will not phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    叠加
    0.41
    為主
    0.41
     rupam
    0.40
    秸
    0.39
     bitOp
    0.37
    就好了
    0.37
    來看
    0.37
    們
    0.37
    肽
    0.37
     intéressant
    0.37
    POSITIVE LOGITS
    也没有
    0.96
    也沒有
    0.92
     tampoco
    0.88
     nor
    0.86
     neither
    0.78
    nor
    0.77
     नहीं
    0.70
    也不能
    0.67
     cannot
    0.67
    也没
    0.66
    Activations Density 0.159%

    No Known Activations