© 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. 34-GEMMASCOPE-RES-131K
    7. 58510
    Prev
    Next
    INDEX
    Explanations

    Western Buddhism, UNC, Immunotoxins

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

    location names and numbers related to addresses or institutional information.

    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_34/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
    ckeye
    -0.81
     sublimation
    -0.76
     urethra
    -0.73
    ifolia
    -0.72
    tubers
    -0.72
     sfor
    -0.71
     chefe
    -0.71
    beg
    -0.71
     seb
    -0.71
    vcut
    -0.70
    POSITIVE LOGITS
     UNC
    0.85
    UNC
    0.84
    gegeven
    0.69
     gues
    0.68
     conscienti
    0.67
     handic
    0.66
    Tar
    0.66
    倉
    0.66
    乙
    0.64
     merely
    0.64
    Activations Density 0.044%

    No Known Activations