© 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. 54241
    Prev
    Next
    INDEX
    Explanations

    NCAA football and automotive vehicles

    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
    prepend
    -0.81
    ራ
    -0.75
    入力
    -0.75
    ctively
    -0.73
     адресу
    -0.72
    idió
    -0.71
    仕事
    -0.71
    École
    -0.71
    本次
    -0.70
    쯔
    -0.70
    POSITIVE LOGITS
     varsity
    1.31
     sponsored
    1.15
     NCAA
    1.04
     budget
    0.98
     offerings
    0.98
     teams
    0.98
     sponsorship
    0.97
     women
    0.94
     sponsor
    0.94
     program
    0.93
    Activations Density 0.039%

    No Known Activations