© 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. 45082
    Prev
    Next
    INDEX
    Explanations

    striatum or striate cortex

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

    anatomical references to the striatum (striatal, striate) in the brain.

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

    This neuron activates on fragmented pieces of the word “striatum,” effectively detecting mentions of that brain region.

    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
    ↵↵
    -3.30
    h
    -3.16
    ra
    -3.02
    O
    -2.98
     we
    -2.92
    r
    -2.81
    変わる
    -2.77
    In
    -2.69
    ce
    -2.64
    ve
    -2.59
    POSITIVE LOGITS
    翃
    3.08
    ſtra
    2.94
     We
    2.91
    
    2.78
     transfé
    2.75
     verminder
    2.73
    疳
    2.72
    迓
    2.70
     indiquer
    2.64
    ৢ
    2.64
    Activations Density 0.009%

    No Known Activations