© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38742
    Prev
    Next
    INDEX
    Explanations

    race times and performances

    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
     When
    -1.15
     Schützen
    -1.12
     new
    -1.12
     now
    -1.10
    érias
    -1.09
     create
    -1.06
    ↵↵
    -1.02
    ↵
    -1.02
    sibilities
    -1.02
     встроен
    -1.01
    POSITIVE LOGITS
     délicieux
    1.44
     unofficial
    1.27
    ⵉ
    1.23
    ータル
    1.22
    dä
    1.19
     udrž
    1.19
     informó
    1.18
    archiwizowane
    1.17
     performances
    1.16
    duino
    1.16
    Activations Density 0.014%

    No Known Activations