© 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. 520
    Prev
    Next
    INDEX
    Explanations

    structural separators

    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
    獴
    -1.60
     descre
    -1.45
    焄
    -1.43
     coincid
    -1.38
     intrig
    -1.29
     antigas
    -1.29
     remol
    -1.28
     Hvor
    -1.27
    ürt
    -1.26
    kingen
    -1.23
    POSITIVE LOGITS
     that
    1.64
     I
    1.45
    of
    1.41
    倨
    1.39
    Ārējās
    1.32
     well
    1.30
    纜
    1.28
     out
    1.28
     dahin
    1.27
    ícias
    1.26
    Activations Density 0.061%

    No Known Activations