© 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. 251487
    Prev
    Next
    INDEX
    Explanations

    rubber band

    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
    遄
    0.52
     विभिन्न
    0.46
    kommun
    0.46
     постро
    0.46
     ლ
    0.46
     hör
    0.45
    KON
    0.44
     म्यूचुअल
    0.44
    َال
    0.44
     privadas
    0.44
    POSITIVE LOGITS
    uffy
    0.50
    asc
    0.49
    ことにより
    0.49
     エネルギー
    0.48
    뱀
    0.46
    အချိန်
    0.44
    oco
    0.43
    쇄
    0.43
    istle
    0.42
     belly
    0.42
    Activations Density 0.001%

    No Known Activations