© 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. 10-GEMMASCOPE-RES-131K
    7. 578
    Prev
    Next
    INDEX
    Explanations

    must have been

    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_10/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
    鹇
    -2.34
    褙
    -2.14
    simply
    -2.08
     facendo
    -2.00
    茈
    -2.00
    幛
    -1.99
    齶
    -1.94
    ₶
    -1.89
     pérd
    -1.89
    榈
    -1.88
    POSITIVE LOGITS
     To
    1.78
    素晴らしい
    1.78
     in
    1.72
     at
    1.72
     impressive
    1.70
     ''
    1.66
     also
    1.63
     quite
    1.60
     måste
    1.59
    lanmış
    1.55
    Activations Density 0.004%

    No Known Activations