© 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. 99672
    Prev
    Next
    INDEX
    Explanations

    permit for, drawer fronts, fit with

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

    French, art, security

    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
    Σ
    0.53
     QnrB
    0.52
     féidir
    0.50
    MACl
    0.48
    pz
    0.47
    互動
    0.47
    watchlist
    0.46
    pozn
    0.46
    indazol
    0.46
    nio
    0.45
    POSITIVE LOGITS
    ↵
    0.59
     a
    0.55
     temptation
    0.52
     réponse
    0.51
     marchand
    0.51
     $
    0.50
     tabular
    0.48
     navigateur
    0.48
     fifteenth
    0.48
     one
    0.48
    Activations Density 0.000%

    No Known Activations