© 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. 11496
    Prev
    Next
    INDEX
    Explanations

    physical postures

    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
    zegor
    -1.23
    |'\
    -1.16
    
    -1.14
    CHELL
    -1.12
    はある
    -1.12
     cardiovas
    -1.11
     évé
    -1.10
    ベージュ
    -1.09
     ۱۸
    -1.09
     Ș
    -1.09
    POSITIVE LOGITS
    G
    1.05
    n
    1.05
    A
    1.03
     хотя
    1.02
     g
    0.99
    is
    0.97
    u
    0.96
    Y
    0.96
     O
    0.94
     northwestern
    0.94
    Activations Density 0.000%

    No Known Activations