© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9471
    Prev
    Next
    INDEX
    Explanations

    key, options, map, style

    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
     also
    -2.16
     to
    -1.76
     troubling
    -1.68
     provides
    -1.62
     or
    -1.60
     with
    -1.59
     bring
    -1.57
     seven
    -1.55
     often
    -1.55
     first
    -1.55
    POSITIVE LOGITS
    
    1.68
     zoude
    1.55
     dezelve
    1.55
     gewi
    1.48
     ランプ
    1.42
    BorderStyle
    1.41
    selben
    1.39
     verhind
    1.38
     cette
    1.38
     STYLE
    1.38
    Activations Density 0.017%

    No Known Activations