© 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. 12163
    Prev
    Next
    INDEX
    Explanations

    state of

    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
    却没有
    -2.50
    也得
    -2.50
     
    -2.36
    湏
    -2.31
     extrêmement
    -2.27
     considérons
    -2.27
     seraient
    -2.27
     "
    -2.25
    Xar
    -2.23
     procurando
    -2.22
    POSITIVE LOGITS
     AspNetCore
    2.75
    ╿
    2.61
     gången
    2.58
    卨
    2.56
    ｢
    2.55
     impeccable
    2.50
    at
    2.48
    　（
    2.47
    as
    2.44
     剤
    2.41
    Activations Density 0.058%

    No Known Activations