© 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. 34-GEMMASCOPE-RES-131K
    7. 1393
    Prev
    Next
    INDEX
    Explanations

    event handler arguments

    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_34/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
    ாம்
    -0.98
     Estaba
    -0.81
    []=$
    -0.80
    >);
    -0.79
    ']=$
    -0.78
    lasi
    -0.78
    ))){
    -0.78
    niów
    -0.77
     fishing
    -0.76
     Grenz
    -0.75
    POSITIVE LOGITS
    object
    1.32
     object
    1.27
     sender
    0.96
     objection
    0.95
    Familia
    0.88
     objected
    0.86
     Cia
    0.81
    OBJECT
    0.80
     ressemb
    0.80
     ヴィ
    0.79
    Activations Density 0.004%

    No Known Activations