© 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. 71448
    Prev
    Next
    INDEX
    Explanations

    actin related terms and Mitch McConnell

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

    The neuron identifies the word "actin" in biological and medical contexts, including references to actin proteins in cell structures and actinic keratosis skin condition.

    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
    袮
    -2.83
    鱟
    -2.77
    枓
    -2.70
    []
    -2.66
    鷓
    -2.61
    鰱
    -2.58
    
    -2.50
     Arquite
    -2.50
     setDate
    -2.45
    古风
    -2.42
    POSITIVE LOGITS
     但
    2.73
     从
    2.69
    在她
    2.61
    但她
    2.55
     señala
    2.52
    是因為
    2.52
    }$.
    2.45
    genodigd
    2.44
    是想
    2.42
    9
    2.41
    Activations Density 0.003%

    No Known Activations