© 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. 124435
    Prev
    Next
    INDEX
    Explanations

    private investigator

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

    locations and sharing

    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
    ể
    0.48
    ią
    0.48
    iteks
    0.46
    _
    0.46
     بزر
    0.46
     ジャ
    0.44
    ğu
    0.44
    )#
    0.44
     відо
    0.44
    že
    0.44
    POSITIVE LOGITS
    casual
    0.46
    curity
    0.45
     Limerick
    0.45
     PROM
    0.45
    CHEC
    0.44
    DETECT
    0.44
    聞
    0.44
    preserving
    0.43
    念念
    0.43
    cannot
    0.42
    Activations Density 0.000%

    No Known Activations