© 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. 34-GEMMASCOPE-RES-131K
    7. 116580
    Prev
    Next
    INDEX
    Explanations

    Ninth Circuit Court of Appeals

    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
    ajā
    -0.82
    roupa
    -0.76
     vegetación
    -0.74
    isFile
    -0.74
     informací
    -0.73
     peacefully
    -0.69
    DIST
    -0.68
    šenie
    -0.68
    ennifer
    -0.68
     semillas
    -0.68
    POSITIVE LOGITS
    cade
    0.79
    ulence
    0.77
    ichel
    0.75
    odend
    0.75
    lets
    0.74
    Updating
    0.73
    ukan
    0.72
    varying
    0.72
    ris
    0.72
    plastic
    0.71
    Activations Density 0.016%

    No Known Activations