© 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. 11112
    Prev
    Next
    INDEX
    Explanations

    all-around / comprehensive

    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
     this
    -1.80
    
    -1.73
    jbl
    -1.63
     Dicapai
    -1.63
     tendrán
    -1.62
    睒
    -1.57
     volledige
    -1.56
     usadas
    -1.55
    
    -1.55
     pasaron
    -1.53
    POSITIVE LOGITS
    .~\
    1.92
    “
    1.88
    mu
    1.86
    ؛
    1.85
    ant
    1.84
    .”
    1.81
    :;
    1.80
    1.74
    ll
    1.71
    vanja
    1.69
    Activations Density 0.004%

    No Known Activations