© 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. 50019
    Prev
    Next
    INDEX
    Explanations

    lower than average census

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

    lists and selections

    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
     Hung
    0.52
     right
    0.47
    Пу
    0.47
     instant
    0.46
    右
    0.45
     Sesam
    0.45
    √
    0.45
    的外
    0.44
     Profit
    0.44
     Ring
    0.44
    POSITIVE LOGITS
    ʏ
    0.46
     carv
    0.44
    㕵
    0.43
     salud
    0.43
    abyte
    0.43
    емом
    0.42
    ayos
    0.42
     disa
    0.42
     জানায়
    0.42
    ov
    0.42
    Activations Density 0.000%

    No Known Activations