© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78654
    Prev
    Next
    INDEX
    Explanations

    SQL data loading syntax

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

    This neuron fires on long sequences of repeated non-alphanumeric characters (e.g. dash lines or punctuation separators).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    敘
    -0.68
    лица
    -0.67
    mr
    -0.66
    躅
    -0.66
    宵
    -0.66
    IMATE
    -0.66
    řel
    -0.65
    lutning
    -0.64
    DetailActivity
    -0.64
    activities
    -0.63
    POSITIVE LOGITS
     red
    0.70
     Menlo
    0.69
    Listar
    0.68
    Leading
    0.68
     iconLine
    0.65
     Brack
    0.63
    Summary
    0.63
    ilina
    0.62
     touristes
    0.62
     satisfy
    0.61
    Activations Density 0.078%

    No Known Activations