© 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. 67763
    Prev
    Next
    INDEX
    Explanations

    cerebral insufficiency or circulation

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

    medical and scientific terms related to the brain and thermal conditions, especially "cerebral" and "Thermo" prefixes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to occurrences of the word “cerebral,” i.e. brain-related terminology.

    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
    ໊
    -3.09
    s
    -2.97
    a
    -2.95
    这件事
    -2.86
     für
    -2.86
    नलोड
    -2.69
    蚡
    -2.69
    鉺
    -2.66
    ⽥
    -2.64
    珦
    -2.63
    POSITIVE LOGITS
    There
    3.09
    "
    2.84
     analyze
    2.52
    開始
    2.42
    Although
    2.41
    ременно
    2.39
     蕾
    2.36
     作り方
    2.30
    独特
    2.27
    '
    2.19
    Activations Density 0.012%

    No Known Activations