© 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. 62444
    Prev
    Next
    INDEX
    Explanations

    license comments

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

    The neuron activates on header or footer/license boilerplate text (copyright, license names, redistribution terms, etc.).

    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
    ومی
    -0.83
     hoffe
    -0.82
    ölf
    -0.80
    rata
    -0.73
     Agarwal
    -0.73
    Ⓖ
    -0.72
     lixo
    -0.71
    porus
    -0.70
     condam
    -0.69
    エール
    -0.69
    POSITIVE LOGITS
     एवं
    0.75
    VEY
    0.73
     needn
    0.70
    ݨ
    0.70
    でもない
    0.68
    veck
    0.67
     which
    0.67
    さに
    0.66
    万一
    0.66
    ローマ
    0.65
    Activations Density 0.038%

    No Known Activations