© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11458
    Prev
    Next
    INDEX
    Explanations

    code structure and parameters

    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
     would
    -1.46
     will
    -1.23
     sowie
    -1.11
     and
    -1.07
     An
    -1.02
     It
    -0.99
     two
    -0.99
     At
    -0.98
     this
    -0.98
    ones
    -0.98
    POSITIVE LOGITS
     buscado
    1.19
     què
    1.14
     détaillé
    1.12
     évident
    1.09
     všech
    1.05
     adatto
    1.05
    Einstellungen
    1.03
     plát
    1.03
     résultat
    1.02
     lavanda
    1.02
    Activations Density 0.015%

    No Known Activations