© 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. 148602
    Prev
    Next
    INDEX
    Explanations

    receiver generate

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

    improves, attempts to, optimized for

    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
    inf
    0.56
    as
    0.47
    Inf
    0.46
    ad
    0.46
    angles
    0.46
    goog
    0.45
    ating
    0.45
    ,
    0.45
    あと
    0.44
    cost
    0.43
    POSITIVE LOGITS
     Новый
    0.54
     Takah
    0.52
     مساعد
    0.49
     새벽
    0.49
     బీ
    0.49
     Muitos
    0.48
     आरो
    0.47
     некоторое
    0.47
     aid
    0.47
     служба
    0.46
    Activations Density 0.000%

    No Known Activations