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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50252
    Prev
    Next
    INDEX
    Explanations

    fat or fate

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

    names with "Fat" or "Fate" prefixes or error messages containing "FATAL".

    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
     useParams
    -0.80
    ajima
    -0.75
    かもし
    -0.75
    quadratic
    -0.74
     Handels
    -0.74
    ディガン
    -0.71
     appContext
    -0.70
    桥
    -0.69
     enmar
    -0.69
     grandeza
    -0.68
    POSITIVE LOGITS
    fat
    1.46
     Fat
    1.38
     FAT
    1.30
     fat
    1.26
    Fat
    1.20
    FAT
    1.13
     fatt
    0.97
     Fats
    0.90
     accompli
    0.88
     Fantas
    0.87
    Activations Density 0.017%

    No Known Activations