© 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. 244120
    Prev
    Next
    INDEX
    Explanations

    cards, apologize, call, day, school

    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
    ིག་
    0.46
     अग्रणी
    0.46
    Trimethyl
    0.45
    ᱞ
    0.44
     régler
    0.43
     guía
    0.42
     আছেন
    0.42
    ાર્
    0.41
    UCKY
    0.41
     punctual
    0.41
    POSITIVE LOGITS
    }\
    0.46
    毫不
    0.46
    precio
    0.44
     Asi
    0.44
    Resultado
    0.44
    سع
    0.44
    NS
    0.43
    лов
    0.43
     অত
    0.42
    全力
    0.42
    Activations Density 0.001%

    No Known Activations