© 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. 194028
    Prev
    Next
    INDEX
    Explanations

    luxury brands and merchandise

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

    for, against, during

    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
     colnames
    0.47
     रतन
    0.46
    冗
    0.46
    ěli
    0.45
     其他
    0.44
     这个
    0.44
    üren
    0.44
    骯
    0.43
    我认为
    0.42
    优点
    0.42
    POSITIVE LOGITS
     produced
    0.48
     supplémentaires
    0.44
     midpoint
    0.44
    Ill
    0.43
    時
    0.43
     resulting
    0.42
    Move
    0.42
     இட
    0.42
     reproducción
    0.42
    ダ
    0.42
    Activations Density 0.001%

    No Known Activations