© 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. 22-GEMMASCOPE-RES-131K
    7. 127910
    Prev
    Next
    INDEX
    Explanations

    The neuron is effectively “dead” – it never fires on any token and thus does not detect any pattern.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    INDIA AT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     με
    -0.91
    else
    -0.90
     to
    -0.88
    criptions
    -0.87
    cookieParser
    -0.85
    acids
    -0.85
     puisqu
    -0.84
    cises
    -0.83
    oys
    -0.83
    ㅅ
    -0.83
    POSITIVE LOGITS
     egip
    1.07
    Ձ
    1.02
    绉
    1.02
    țiile
    1.01
    他们是
    1.00
     aproximado
    1.00
    Pendant
    0.97
    釈
    0.96
    ֩
    0.96
     before
    0.95
    Activations Density 0.001%

    No Known Activations