© 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. 181976
    Prev
    Next
    INDEX
    Explanations

    company announcements

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

    King Croesus, updates

    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
     V
    0.46
    তারপর
    0.46
     JOY
    0.45
    ,//
    0.45
     SIGN
    0.44
    আমাকে
    0.44
     farmer
    0.44
     Mayor
    0.43
     Commander
    0.43
     buz
    0.43
    POSITIVE LOGITS
    沓
    0.46
     이유는
    0.46
    demon
    0.43
    恋爱
    0.42
    aquest
    0.42
    istiche
    0.42
    etri
    0.42
    かは
    0.42
     подобных
    0.41
    内容は
    0.41
    Activations Density 0.001%

    No Known Activations