© 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. 201282
    Prev
    Next
    INDEX
    Explanations

    solve cold cases

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

    specific items or concepts

    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
    ن
    0.49
    Y
    0.45
     nummer
    0.45
    //
    0.44
    acto
    0.43
    न
    0.43
    คร
    0.42
    uega
    0.41
     snowflakes
    0.41
     languages
    0.41
    POSITIVE LOGITS
     ভোট
    0.55
     গাড়
    0.55
     옳은
    0.54
    𒉈
    0.54
     опас
    0.53
     सच्चे
    0.53
    暊
    0.52
    璺
    0.50
     সঙ্গে
    0.49
    㜌
    0.48
    Activations Density 0.001%

    No Known Activations