© 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. 164964
    Prev
    Next
    INDEX
    Explanations

    via email, translated into

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

    quickly, violent, peppers, pesticide, warm

    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
     mortgages
    0.48
    shopping
    0.43
    커
    0.43
     mites
    0.42
    ܡ
    0.42
    duc
    0.42
    offs
    0.42
     seuls
    0.42
     costas
    0.42
    ⴽ
    0.41
    POSITIVE LOGITS
     Trên
    0.51
    两大
    0.49
    按照
    0.49
     Swagger
    0.48
     Turn
    0.47
     ইচ্ছ
    0.47
     Choosing
    0.46
     Choose
    0.46
     Authorized
    0.46
     Doğ
    0.45
    Activations Density 0.000%

    No Known Activations