© 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. 34-GEMMASCOPE-RES-131K
    7. 94196
    Prev
    Next
    INDEX
    Explanations

    HARTFORD

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

    The neuron primarily detects capitalized named entities—especially personal names, official titles, and related political or organizational designations.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    both
    -0.96
    epen
    -0.89
     např
    -0.83
    洸
    -0.83
     díky
    -0.81
     veramente
    -0.78
    也都
    -0.76
     vielleicht
    -0.75
    ってきて
    -0.75
    xxxxxxxxxxxxxxxx
    -0.75
    POSITIVE LOGITS
     Wednesday
    0.87
     паке
    0.85
     Tuesday
    0.85
    Prime
    0.83
    manifold
    0.76
     Prime
    0.76
    parken
    0.76
    million
    0.76
     Thursday
    0.75
    북
    0.75
    Activations Density 0.008%

    No Known Activations