© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    dobutamine, Dov, Dobrushin

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

    names or proper nouns with the prefix "Dob" or similar syllables.

    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
    RIED
    -0.85
     calmness
    -0.84
    тур
    -0.79
    sitions
    -0.76
     folha
    -0.75
    смотра
    -0.75
     Soak
    -0.74
     overjoyed
    -0.73
    combobox
    -0.73
    ན་
    -0.72
    POSITIVE LOGITS
    ví
    0.76
    ieg
    0.74
     entier
    0.73
     formaldehyde
    0.69
     Erkrankungen
    0.68
     inactivation
    0.68
    િક
    0.68
    kins
    0.68
     ulcer
    0.66
    幾個
    0.66
    Activations Density 0.020%

    No Known Activations