© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44434
    Prev
    Next
    INDEX
    Explanations

    regulating gene expression or biological processes

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

    verbs related to controlling, operating, or directing actions or processes.

    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
     \
    -1.76
     father
    -1.59
    restling
    -1.55
    ing
    -1.54
    s
    -1.53
    ｋ
    -1.52
    Ｒ
    -1.49
     ganze
    -1.48
    Ｅ
    -1.48
     haven
    -1.48
    POSITIVE LOGITS
     ainfi
    1.93
     eenen
    1.86
    笵
    1.79
    齜
    1.67
     koste
    1.67
     boute
    1.66
     oock
    1.65
    壜
    1.63
    푏
    1.62
     casque
    1.60
    Activations Density 0.009%

    No Known Activations