© 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. 31909
    Prev
    Next
    INDEX
    Explanations

    phone numbers and emails

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

    applicable rates

    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
    я
    0.58
    ту
    0.56
    ט
    0.52
    тики
    0.52
    со
    0.51
    у
    0.50
    ма
    0.50
    бу
    0.49
    ар
    0.48
    ја
    0.48
    POSITIVE LOGITS
    lever
    0.52
     الإن
    0.48
     Establish
    0.45
     decreto
    0.44
    hauer
    0.44
    暐
    0.44
     Strukturen
    0.44
     Leistung
    0.43
     Basel
    0.43
     eingesetzt
    0.43
    Activations Density 0.000%

    No Known Activations