© 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. 174477
    Prev
    Next
    INDEX
    Explanations

    celebrity names or artist names

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

    virtual machines

    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
     افت
    0.50
     সাথে
    0.45
    같이
    0.44
     ठिकाणी
    0.43
    ጠር
    0.43
    ຽ
    0.42
     권
    0.42
     정
    0.42
    顫
    0.41
    აბ
    0.41
    POSITIVE LOGITS
    jskim
    0.52
     irá
    0.49
    NaBH
    0.49
     stammt
    0.48
    Farmer
    0.48
    ZrO
    0.46
     northbound
    0.46
     চেতনা
    0.46
     hastened
    0.46
     Gaspar
    0.46
    Activations Density 0.001%

    No Known Activations