© 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. 160224
    Prev
    Next
    INDEX
    Explanations

    adverse effects, purchased item, Los Angeles

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

    sex and negative relationships

    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
     `'\\
    0.51
     Balliye
    0.47
     Фургала
    0.47
    amini
    0.46
     المثلثيه
    0.46
     የበለጠ
    0.45
     বণিক
    0.44
     rétréci
    0.44
     Jolla
    0.44
    loadConst
    0.44
    POSITIVE LOGITS
    儿
    0.47
     dashed
    0.47
     dashes
    0.46
    виси
    0.46
     frustrations
    0.45
     tasas
    0.45
    ти
    0.45
    ний
    0.45
     años
    0.44
    β
    0.43
    Activations Density 0.000%

    No Known Activations