© 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. 12283
    Prev
    Next
    INDEX
    Explanations

    medical investigation and biological context

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical values, particularly dates, ages, and numbers in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     or
    -1.48
     you
    -1.41
    What
    -1.38
     what
    -1.34
     However
    -1.33
     If
    -1.33
    に見える
    -1.33
     Although
    -1.32
     With
    -1.27
    You
    -1.26
    POSITIVE LOGITS
    その
    1.39
    こい
    1.23
    
    1.20
     oogen
    1.19
    が
    1.18
     entidade
    1.14
    Mvh
    1.13
     furia
    1.12
     uyt
    1.11
     eene
    1.10
    Activations Density 0.020%

    No Known Activations