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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11318
    Prev
    Next
    INDEX
    Explanations

    xml attributes and values

    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
     in
    -2.28
     by
    -1.96
     all
    -1.90
     have
    -1.85
     (
    -1.74
     from
    -1.70
     even
    -1.69
     get
    -1.64
     will
    -1.59
     with
    -1.55
    POSITIVE LOGITS
     angesehen
    1.76
     zuständig
    1.55
     valoraciones
    1.54
     reemplazar
    1.53
     secluded
    1.53
     magnificent
    1.52
     anerkannt
    1.52
     verschillende
    1.51
     evaluaciones
    1.48
     beliebt
    1.47
    Activations Density 0.008%

    No Known Activations