© 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. 57367
    Prev
    Next
    INDEX
    Explanations

    code comments and file headers

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

    The neuron primarily activates on sequences of digits, i.e. numeric literals.

    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
     successivo
    -0.84
     viņ
    -0.81
    Ken
    -0.77
     発売
    -0.73
     sarili
    -0.71
     BERNAMA
    -0.69
    couvrir
    -0.69
     movimenti
    -0.69
     dzī
    -0.69
     cilvē
    -0.69
    POSITIVE LOGITS
    Connecticut
    0.87
     Connecticut
    0.86
     Mawr
    0.84
    Pus
    0.83
    adomo
    0.81
    ."/
    0.81
    阅读原文
    0.79
    ⡟
    0.78
    缎
    0.75
    ïti
    0.75
    Activations Density 0.011%

    No Known Activations