© 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. 211288
    Prev
    Next
    INDEX
    Explanations

    UK foreign

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

    two children

    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
    ⺠
    0.52
    тения
    0.50
     Миха
    0.49
    𒆳
    0.48
     медици
    0.47
    InputBorder
    0.47
    ם
    0.47
    コマンド
    0.47
     профилакти
    0.46
     канал
    0.46
    POSITIVE LOGITS
    s
    0.64
    r
    0.56
    0
    0.54
    R
    0.52
     hack
    0.51
    n
    0.51
    (
    0.50
     hill
    0.50
    rol
    0.50
    acking
    0.49
    Activations Density 0.000%

    No Known Activations