© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64113
    Prev
    Next
    INDEX
    Explanations

    sports records and achievements

    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
     vírus
    -0.75
    reys
    -0.75
    İyi
    -0.75
     reveal
    -0.73
    ́t
    -0.73
    spring
    -0.72
    NegativeButton
    -0.71
     staffing
    -0.70
     mercies
    -0.70
     Erfahrungen
    -0.69
    POSITIVE LOGITS
     record
    1.60
    record
    1.32
     surpassed
    1.27
     records
    1.24
     surpassing
    1.21
     Record
    1.15
     career
    1.13
     рекор
    1.13
    Record
    1.07
     surpass
    1.07
    Activations Density 0.027%

    No Known Activations