© 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. 115610
    Prev
    Next
    INDEX
    Explanations

    SYSTEM identifier

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

    garden proportions

    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
    ртом
    0.51
    沼
    0.48
    ologisch
    0.46
    நாம
    0.46
    日で
    0.45
    rump
    0.45
    ニュー
    0.45
    ificaciones
    0.44
     extranjero
    0.44
    ่อ
    0.44
    POSITIVE LOGITS
    ت
    0.51
     Xt
    0.50
     Sch
    0.48
     Z
    0.48
     ઊ
    0.47
     Vf
    0.46
    paren
    0.43
     ക്യാ
    0.43
     valu
    0.43
     seh
    0.43
    Activations Density 0.000%

    No Known Activations