© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90329
    Prev
    Next
    INDEX
    Explanations

    Scriptable Object Instance

    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
     as
    -2.48
     people
    -2.28
     with
    -2.08
     one
    -2.08
     new
    -2.03
     presumably
    -2.03
     or
    -1.99
     despite
    -1.98
     including
    -1.97
     when
    -1.96
    POSITIVE LOGITS
     jezt
    1.82
     DÉ
    1.73
     luy
    1.61
    
    1.60
     gewi
    1.58
    棡
    1.56
     auffi
    1.52
    簓
    1.52
     raconter
    1.52
    verkauf
    1.52
    Activations Density 0.195%

    No Known Activations