© 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. 64087
    Prev
    Next
    INDEX
    Explanations

    size and dimensions

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

    The neuron fires on numeric literals (sequences of digits) appearing in markup or code.

    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
     tho
    -0.79
    おじ
    -0.78
    侥
    -0.77
    ornadas
    -0.77
    ☼
    -0.77
    ✷
    -0.76
     %#
    -0.76
    ='';
    -0.74
    ாள
    -0.74
     Пав
    -0.73
    POSITIVE LOGITS
    size
    0.95
     Größe
    0.85
     Aufführung
    0.80
    Quora
    0.77
     карти
    0.77
    mendous
    0.76
    ):(
    0.75
     telegram
    0.75
    arh
    0.74
    comme
    0.74
    Activations Density 0.037%

    No Known Activations