© 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. 10-GEMMASCOPE-RES-131K
    7. 129581
    Prev
    Next
    INDEX
    Explanations

    describing how things look

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

    The neuron fires strongly on occurrences of the verb “look” (including “looks”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    棪
    -1.58
    鸸
    -1.52
    戽
    -1.47
    FFEE
    -1.47
     diversión
    -1.43
     海报
    -1.38
    それで
    -1.37
     Crédito
    -1.37
     sû
    -1.36
     thirteen
    -1.36
    POSITIVE LOGITS
    1
    2.16
    7
    2.16
    8
    2.11
    4
    1.93
    3
    1.92
    0
    1.87
    9
    1.87
    一些
    1.76
    </h2>
    1.74
     how
    1.67
    Activations Density 0.005%

    No Known Activations