© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101347
    Prev
    Next
    INDEX
    Explanations

    resistance, session, store

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

    the beginning of class or function definitions in code, particularly after annotations or decorators.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     estadounid
    -1.72
     bénévol
    -1.66
     emballage
    -1.60
     barcel
    -1.59
     étoient
    -1.54
     laboratorium
    -1.54
     rabat
    -1.52
    Läs
    -1.52
    ちゃった
    -1.51
     ориги
    -1.50
    POSITIVE LOGITS
     
    2.56
     "
    2.11
     özellikle
    1.81
     [
    1.73
     is
    1.70
     ”
    1.67
    ↵↵
    1.66
     —
    1.56
    —
    1.53
    ,"
    1.51
    Activations Density 0.016%

    No Known Activations