© 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. 113051
    Prev
    Next
    INDEX
    Explanations

    Dorothy platelets PRP

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

    proper names, particularly female first names like Dorothy, Pauline, and Colleen.

    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
    to
    -2.58
    E
    -2.50
    u
    -2.45
    \
    -2.42
    真的是
    -2.34
     With
    -2.33
    of
    -2.33
     WITH
    -2.23
    情況
    -2.19
     корпус
    -2.19
    POSITIVE LOGITS
    ’
    2.95
    聼
    2.67
    㐂
    2.61
    尛
    2.61
    畱
    2.58
    
    2.53
    -“
    2.48
     walaupun
    2.45
     ERSITY
    2.45
    鋮
    2.44
    Activations Density 0.016%

    No Known Activations