© 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. 206811
    Prev
    Next
    INDEX
    Explanations

    shine; Fix Tool; Software source; not justify

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

    break, accuracy, downloading, data quality, purpose

    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
    મ
    0.50
    p
    0.50
    ט
    0.50
    ש
    0.47
    色
    0.47
    MORDOR
    0.46
    தம்ப
    0.45
    та
    0.45
    פ
    0.45
    さら
    0.45
    POSITIVE LOGITS
     บาง
    0.55
     transacción
    0.46
     พูด
    0.46
     विशाल
    0.45
     แพ
    0.44
     vissa
    0.44
     voitures
    0.44
    েকে
    0.43
     পথে
    0.43
     รถ
    0.42
    Activations Density 0.001%

    No Known Activations