© 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. 22-GEMMASCOPE-RES-131K
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    AP, NHL, Soccer

    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_22/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
     profils
    -0.92
     vicini
    -0.90
    Incluso
    -0.90
     mélanger
    -0.85
    を選び
    -0.85
    Actualmente
    -0.84
    acyjny
    -0.84
     resemblance
    -0.84
    olding
    -0.84
     médicaments
    -0.83
    POSITIVE LOGITS
     only
    1.06
     also
    1.01
     area
    0.85
     due
    0.84
     только
    0.83
     based
    0.82
     Due
    0.80
    ortes
    0.79
    estinian
    0.79
    due
    0.79
    Activations Density 0.005%

    No Known Activations