© 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. 32247
    Prev
    Next
    INDEX
    Explanations

    resistance against

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

    john smith, micro structures, date of birth

    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
    MORD
    0.45
    ඕ
    0.44
    各自
    0.44
    FRED
    0.44
    いは
    0.44
    ゼロ
    0.43
    ZER
    0.43
    いっぱい
    0.42
    валась
    0.42
    insuff
    0.42
    POSITIVE LOGITS
     Na
    0.53
     N
    0.52
     calend
    0.47
     Races
    0.46
     H
    0.46
     AB
    0.45
     sodium
    0.45
     Sko
    0.45
     racing
    0.45
     kit
    0.44
    Activations Density 0.000%

    No Known Activations