© 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. 22-GEMMASCOPE-RES-131K
    7. 65586
    Prev
    Next
    INDEX
    Explanations

    View of Geography

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

    The neuron spikes on numeric and symbolic tokens (digits, hyphens, equals signs, etc.) used in headings, lists, or other document‐formatting elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    =>"
    -1.16
    tront
    -1.12
     exager
    -1.12
    lustre
    -1.10
     mètres
    -1.09
     eſſ
    -1.09
     ſol
    -1.09
    kami
    -1.09
     sement
    -1.08
    %",
    -1.07
    POSITIVE LOGITS
     you
    1.46
     also
    1.33
     berücksich
    1.09
    Dusk
    0.96
     озна
    0.95
     other
    0.95
     puedes
    0.91
     good
    0.90
     olvidado
    0.90
     research
    0.89
    Activations Density 0.001%

    No Known Activations