© 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. 511
    Prev
    Next
    INDEX
    Explanations

    anal followed by medical or sexual terms

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

    the word "anal" used both anatomically and metaphorically.

    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_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
    ’
    -3.23
    sandalia
    -3.13
     แต่
    -2.94
    囖
    -2.73
    
    -2.66
     But
    -2.63
    archiwizowane
    -2.59
    NOMBRE
    -2.55
     semelh
    -2.52
     Our
    -2.50
    POSITIVE LOGITS
    For
    3.48
    A
    3.47
    T
    3.23
    C
    3.19
    To
    3.05
    E
    3.02
    7
    2.97
    B
    2.86
    re
    2.84
    the
    2.84
    Activations Density 0.003%

    No Known Activations