© 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. 66922
    Prev
    Next
    INDEX
    Explanations

    check it out

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

    look for micro-tasks

    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
    首席
    0.41
    匿名
    0.39
    分散
    0.39
    ahassee
    0.37
     خاصيه
    0.37
    ゲスト
    0.37
    籐
    0.37
    態
    0.36
    Order
    0.36
    推定
    0.36
    POSITIVE LOGITS
     окру
    0.45
     biotechnology
    0.44
    wej
    0.44
     ocz
    0.42
     interestingly
    0.42
     fruto
    0.42
     ellát
    0.42
    யில
    0.41
     ihan
    0.41
    alakip
    0.41
    Activations Density 0.002%

    No Known Activations