© 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. 244808
    Prev
    Next
    INDEX
    Explanations

    Support, Jimmy, Lee

    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
    နှ
    0.45
    सादर
    0.44
    ح
    0.44
    uyền
    0.44
     ministerial
    0.43
     minister
    0.43
     bombings
    0.42
     guère
    0.42
    র্
    0.42
     punishable
    0.41
    POSITIVE LOGITS
    \</
    0.45
     υπάρχ
    0.44
    CURRENT
    0.43
    さらに
    0.42
     descu
    0.41
    開始
    0.40
     كتاب
    0.40
    lst
    0.40
    डील
    0.40
     Finley
    0.40
    Activations Density 0.001%

    No Known Activations