© 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. 78633
    Prev
    Next
    INDEX
    Explanations

    questions, titles, or names

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

    The neuron flags tokens composed primarily of digits or digit‐heavy strings (e.g. dates, article ID numbers, URL numeric segments).

    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
     INVESTIGATION
    -0.91
    င
    -0.79
     Investigation
    -0.76
     UPDATED
    -0.75
    Investigation
    -0.75
     unsur
    -0.74
    onUpdate
    -0.74
    褰
    -0.73
    כנ
    -0.73
     investigation
    -0.73
    POSITIVE LOGITS
     ET
    1.22
    ET
    0.87
    είου
    0.78
     Constantinople
    0.75
     anfitrión
    0.75
    alista
    0.74
    tablir
    0.74
    olge
    0.74
    <thead>
    0.73
    umer
    0.73
    Activations Density 0.007%

    No Known Activations