© 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. 59507
    Prev
    Next
    INDEX
    Explanations

    mathematical typesetting environments

    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
    天候
    -0.78
     enää
    -0.73
     embreagem
    -0.71
    ί
    -0.70
     Leiden
    -0.69
    CAPTURE
    -0.69
    狭い
    -0.69
    ungalow
    -0.69
    ziell
    -0.68
    marque
    -0.68
    POSITIVE LOGITS
     Pigeon
    0.86
    ầm
    0.82
    İZ
    0.80
     липня
    0.80
     parishi
    0.76
    Parameter
    0.74
     Anliegen
    0.73
    initas
    0.73
    ení
    0.72
    Images
    0.72
    Activations Density 0.021%

    No Known Activations