© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99029
    Prev
    Next
    INDEX
    Explanations

    blind / blinded / blinding

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

    This neuron responds to words and phrases describing blindness or visual impairment.

    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
    </h3>
    -2.19
    <bos>
    -2.13
    這
    -2.03
    tedì
    -2.03
    This
    -2.03
    "));
    -1.88
    </i>
    -1.86
    ,’
    -1.86
    ⎽
    -1.84
     elaborado
    -1.77
    POSITIVE LOGITS
     The
    2.30
     "
    1.99
     {"
    1.84
    ке
    1.81
    л
    1.78
    蔸
    1.74
    鸶
    1.73
     $\
    1.67
     puissant
    1.64
     blinding
    1.64
    Activations Density 0.004%

    No Known Activations