© 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. 197831
    Prev
    Next
    INDEX
    Explanations

    endings, specifications, or points in time

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

    sections for different

    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
     morte
    0.43
     conhecida
    0.43
    GridView
    0.42
     hatte
    0.41
    dbname
    0.41
     शिव
    0.40
     denture
    0.40
    泰
    0.39
    居然
    0.39
     بودند
    0.39
    POSITIVE LOGITS
    につなが
    0.52
     አስተ
    0.50
     Latitude
    0.48
    ק
    0.48
    bajo
    0.47
     ተግባ
    0.47
     ሁ
    0.47
     ሀ
    0.47
     ادي
    0.47
     ምስ
    0.46
    Activations Density 0.000%

    No Known Activations