© 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. 142174
    Prev
    Next
    INDEX
    Explanations

    commercial and planning details

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

    recommendations and options

    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
     phun
    0.49
     défendre
    0.47
    URE
    0.44
    жать
    0.43
    들이
    0.43
    輋
    0.43
    叠加
    0.43
    واد
    0.42
     защиты
    0.42
     geben
    0.42
    POSITIVE LOGITS
    az
    0.56
    ン
    0.55
    att
    0.54
    su
    0.52
    ema
    0.50
    orc
    0.46
    ent
    0.46
    ス
    0.46
    ឌ
    0.45
    ム
    0.45
    Activations Density 0.001%

    No Known Activations