© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32445
    Prev
    Next
    INDEX
    Explanations

    GH, EF, AB, JK, RS

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

    The neuron is specialized in picking out numeric tokens (stand-alone digits and multi-digit numbers) in code or data contexts.

    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
     reper
    -0.74
    循
    -0.73
    ddha
    -0.72
     impound
    -0.72
     Lel
    -0.71
     Safer
    -0.71
     pierwszy
    -0.71
     càng
    -0.71
     itineraries
    -0.71
    laze
    -0.69
    POSITIVE LOGITS
    EF
    1.09
     EF
    0.90
     JK
    0.84
     RS
    0.81
     AB
    0.80
     MN
    0.78
     classic
    0.77
    RS
    0.76
    jk
    0.76
    Among
    0.76
    Activations Density 0.047%

    No Known Activations