© 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. 32437
    Prev
    Next
    INDEX
    Explanations

    short phrases or states

    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
     競
    -0.82
    駒
    -0.70
     Meri
    -0.70
     கு
    -0.70
    PROPERTY
    -0.69
     च
    -0.69
     UML
    -0.69
    pezifische
    -0.69
     känd
    -0.69
    Pu
    -0.69
    POSITIVE LOGITS
     staffed
    0.91
    falls
    0.88
    Falls
    0.78
    manta
    0.78
     schrift
    0.76
     fall
    0.76
     of
    0.75
     FALLS
    0.73
     sighted
    0.73
    wsze
    0.73
    Activations Density 0.025%

    No Known Activations