© 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. 94683
    Prev
    Next
    INDEX
    Explanations

    advice and descriptions

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

    thorough and comprehensive explanations

    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
    י
    0.57
    ي
    0.53
     estudante
    0.48
    アプリ
    0.45
     grapevine
    0.44
    テーブル
    0.43
    ستی
    0.43
     deport
    0.42
     privada
    0.42
    య
    0.42
    POSITIVE LOGITS
    ikir
    0.54
    atiti
    0.52
    hud
    0.50
    arder
    0.49
    Width
    0.49
    MCs
    0.48
    ers
    0.47
    TK
    0.45
    FormControl
    0.45
    axie
    0.44
    Activations Density 0.001%

    No Known Activations