© 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. 48431
    Prev
    Next
    INDEX
    Explanations

    licensing and code structure

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

    The neuron predominantly fires on numeric tokens (digits and numbers) in the text.

    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
    Http
    -0.80
    陌生
    -0.78
     trực
    -0.75
     博
    -0.73
     địch
    -0.71
    げん
    -0.71
    lick
    -0.70
     ladrillo
    -0.68
     znale
    -0.67
    Quat
    -0.67
    POSITIVE LOGITS
     PowerPoint
    0.68
     အ
    0.67
    ieden
    0.66
    カラオケ
    0.65
     unen
    0.65
    uther
    0.65
     sash
    0.65
    lussen
    0.65
     caribou
    0.64
    处
    0.64
    Activations Density 0.030%

    No Known Activations