© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59369
    Prev
    Next
    INDEX
    Explanations

    work with files, Hewlett-Packard, GetObject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ܆
    -2.30
    缑
    -2.17
    やら
    -2.06
    様の
    -2.06
     используется
    -2.05
    ╽
    -2.03
    StoryboardSegue
    -1.98
     другим
    -1.98
    ᡝ
    -1.98
    НЫХ
    -1.97
    POSITIVE LOGITS
    ↵
    3.31
     unangemess
    2.77
    不得不说
    2.69
    -“
    2.64
    [
    2.61
     vollständ
    2.53
    ⇰
    2.52
    
    2.48
     Auseinander
    2.39
     Not
    2.30
    Activations Density 0.007%

    No Known Activations