© 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. 22-GEMMASCOPE-RES-131K
    7. 38743
    Prev
    Next
    INDEX
    Explanations

    bull compounds

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

    The neuron detects variations of the word "Bull" (Bullfrog, Bulls, Bulbapedia, Bulgarian, etc.).

    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_22/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
     antiguas
    -2.56
    蔔
    -2.48
    wiście
    -2.42
     recientes
    -2.33
    ↵
    -2.33
     peores
    -2.25
    贗
    -2.25
     flesta
    -2.25
    ↵↵
    -2.22
     municipales
    -2.20
    POSITIVE LOGITS
    1
    3.45
    2
    2.94
    亊
    2.89
    𓆜
    2.75
    錸
    2.63
    孥
    2.63
    
    2.61
    </strong>
    2.53
    蛲
    2.36
     女人
    2.33
    Activations Density 0.016%

    No Known Activations