© 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. 29942
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

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

    The neuron selectively activates on long alphanumeric digit sequences—e.g. hex dumps, long numeric IDs, coordinates or version/build numbers—rather than ordinary words.

    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
     большим
    -0.87
     recente
    -0.84
     muzik
    -0.84
    FFFFFFFF
    -0.83
    ίο
    -0.83
     komme
    -0.81
     dette
    -0.81
     odio
    -0.80
     scén
    -0.79
    ботинки
    -0.79
    POSITIVE LOGITS
    Most
    1.05
    Quite
    0.83
    撰
    0.79
    There
    0.78
    When
    0.75
     their
    0.75
     affects
    0.72
    Shortly
    0.72
     invierno
    0.71
    حص
    0.71
    Activations Density 0.049%

    No Known Activations