© 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. 11446
    Prev
    Next
    INDEX
    Explanations

    properties and configurations

    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
     не
    -0.94
     neither
    -0.94
    なども
    -0.93
     ничего
    -0.90
    Não
    -0.88
     which
    -0.88
     relatively
    -0.86
    nothing
    -0.81
    ებ
    -0.81
    leading
    -0.80
    POSITIVE LOGITS
    apore
    1.09
    nikon
    1.02
    korean
    0.95
    partie
    0.94
     ficando
    0.91
     feminina
    0.90
     administratif
    0.88
     manqué
    0.88
     kinda
    0.87
    nses
    0.86
    Activations Density 0.027%

    No Known Activations