© 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. 21866
    Prev
    Next
    INDEX
    Explanations

    string value explanations

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

    string types and usage

    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
     piercings
    0.50
     hyperactivity
    0.46
     vectores
    0.45
     enzymes
    0.45
     inflammation
    0.44
     vectors
    0.44
    ustering
    0.43
    َهُ
    0.43
     biopsies
    0.43
     {.
    0.42
    POSITIVE LOGITS
    字符串
    0.89
    String
    0.81
    文字列
    0.81
     string
    0.77
     String
    0.74
    NSString
    0.73
     substring
    0.71
     ToString
    0.70
    AsString
    0.70
    Substring
    0.69
    Activations Density 0.003%

    No Known Activations