© 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. 60202
    Prev
    Next
    INDEX
    Explanations

    College Sports

    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
     Oils
    -0.87
    uvwxyz
    -0.81
     oils
    -0.78
     ignorant
    -0.76
    лович
    -0.73
     alcuni
    -0.71
    ticians
    -0.69
     조회
    -0.69
    しか
    -0.69
     영화
    -0.69
    POSITIVE LOGITS
    ğa
    0.80
     Medium
    0.78
     tightened
    0.77
    Titus
    0.75
    UpdatedAt
    0.75
     tighter
    0.75
     изо
    0.75
    effic
    0.70
    ^{-}\
    0.70
     tighten
    0.69
    Activations Density 0.013%

    No Known Activations