© 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. 33261
    Prev
    Next
    INDEX
    Explanations

    Tom Clancy books

    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
    ɫ
    -0.79
     vostro
    -0.76
     überweisen
    -0.75
    Mysql
    -0.73
     Aufenthalt
    -0.71
     restoring
    -0.70
    謨
    -0.69
    pkins
    -0.67
     tribun
    -0.67
     restore
    -0.67
    POSITIVE LOGITS
     Rainbow
    1.04
     Ubi
    0.96
    Rainbow
    0.93
     ubi
    0.92
    operators
    0.88
     Siege
    0.84
     Gadgets
    0.84
    operator
    0.84
     Forester
    0.84
    Ubi
    0.84
    Activations Density 0.014%

    No Known Activations