© 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. 67831
    Prev
    Next
    INDEX
    Explanations

    evoked potentials or responses

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

    The neuron detects the word "evoked" and its various forms, particularly when followed by prepositions like "in," "a," or "by."

    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
    蜴
    -2.66
    man
    -2.59
    紧接着
    -2.47
    憮
    -2.45
    how
    -2.45
     سریع
    -2.41
    几十
    -2.34
    一个月
    -2.31
    C
    -2.31
    黢
    -2.30
    POSITIVE LOGITS
     necesariamente
    2.47
    
    2.34
    ℟
    2.33
     ampliamente
    2.31
     supuestamente
    2.28
    錞
    2.27
     reempla
    2.25
     amenaz
    2.20
    ственные
    2.20
    ︓
    2.17
    Activations Density 0.004%

    No Known Activations