© 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. 238908
    Prev
    Next
    INDEX
    Explanations

    change, patience, required, names

    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
    दीप
    0.48
    यों
    0.45
    цію
    0.45
    𓂃
    0.44
    ЕН
    0.43
     segmented
    0.42
     dục
    0.42
     جوسینو
    0.41
    gameState
    0.41
     سلاټ
    0.41
    POSITIVE LOGITS
     hver
    0.52
    欣賞
    0.49
     znamená
    0.48
     Clair
    0.47
    wä
    0.47
     freund
    0.46
    鐧
    0.46
    rzej
    0.45
    త్ర
    0.45
     পরিচ
    0.45
    Activations Density 0.001%

    No Known Activations