© 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. 22-GEMMASCOPE-RES-131K
    7. 38691
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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_22/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
     diminish
    -1.63
    嗞
    -1.43
     brune
    -1.41
    Она
    -1.40
     bebes
    -1.40
    ディション
    -1.39
    Его
    -1.38
    ┊
    -1.36
    Например
    -1.31
     fald
    -1.30
    POSITIVE LOGITS
     algunos
    1.67
     ciertos
    1.60
    
    1.55
    grats
    1.48
    enablog
    1.45
    %
    1.44
     besonder
    1.43
     conceito
    1.42
     comércio
    1.42
     freie
    1.41
    Activations Density 0.037%

    No Known Activations