© 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. 193344
    Prev
    Next
    INDEX
    Explanations

    cause and effect

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

    employee classifications

    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
     డబ్బు
    0.50
     يخ
    0.48
    Escolhido
    0.48
    pei
    0.48
    iculas
    0.47
    toMap
    0.47
    𝖐
    0.47
    popupIsOpen
    0.46
    ངས་
    0.46
    žd
    0.46
    POSITIVE LOGITS
     Aubrey
    0.47
     attacked
    0.45
    <em>
    0.45
     Sushi
    0.44
    然
    0.44
     William
    0.43
     severance
    0.43
     It
    0.43
     embedded
    0.43
    る
    0.43
    Activations Density 0.000%

    No Known Activations