© 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. 34-GEMMASCOPE-RES-131K
    7. 116234
    Prev
    Next
    INDEX
    Explanations

    hair colors, styles, and states

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

    The neuron detects descriptions of hair (its color, texture, or motion).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Skincare
    -1.09
     bearded
    -0.88
     hairy
    -0.87
    áky
    -0.87
    illium
    -0.84
     skincare
    -0.83
    цтва
    -0.82
     leurs
    -0.82
    ệng
    -0.82
     TEL
    -0.81
    POSITIVE LOGITS
     strands
    1.18
     unruly
    1.04
     helmet
    0.94
     Helmet
    0.90
    Helmet
    0.86
    helmet
    0.86
     combed
    0.84
     styled
    0.82
     fios
    0.82
     tous
    0.82
    Activations Density 0.020%

    No Known Activations