© 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. 73357
    Prev
    Next
    INDEX
    Explanations

    regrets WAIVER Rights

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

    Twin Towers, myBurgerLab, Hoi An, Nobel himself

    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
    utter
    0.47
    ancellor
    0.46
    ordinator
    0.44
    ateral
    0.44
    6
    0.44
    init
    0.43
     titul
    0.42
    umerate
    0.41
    <code>
    0.41
    isel
    0.40
    POSITIVE LOGITS
     flirt
    0.56
     वस्तू
    0.49
     flirting
    0.49
     واس
    0.49
    楕
    0.48
    拡散方程式
    0.47
    物を
    0.47
    өн
    0.46
     инструмент
    0.46
    食器
    0.46
    Activations Density 0.001%

    No Known Activations