© 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. 77324
    Prev
    Next
    INDEX
    Explanations

    Q: or In:

    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
     volte
    -0.82
    🐍
    -0.81
     parto
    -0.81
    harusnya
    -0.79
     Concer
    -0.78
     yaml
    -0.77
    contacto
    -0.76
     claire
    -0.74
     involunt
    -0.73
    ➛
    -0.73
    POSITIVE LOGITS
    férences
    0.97
     Schedule
    0.91
    Theme
    0.85
    𝓐
    0.83
     Theme
    0.82
    Schedule
    0.80
    Austin
    0.80
     ohne
    0.79
    Editor
    0.78
    例
    0.78
    Activations Density 0.003%

    No Known Activations