© 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. 15185
    Prev
    Next
    INDEX
    Explanations

    end of line characters

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

    The neuron activates on numeric literals (integer or floating‐point constants) embedded in code.

    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
     to
    -1.09
     fünf
    -1.01
    geq
    -1.00
    werking
    -0.96
    begin
    -0.95
     VERY
    -0.88
     ersten
    -0.84
     Mitteln
    -0.83
     verschiedenen
    -0.82
     Bereichen
    -0.82
    POSITIVE LOGITS
    Продол
    1.14
     hilos
    1.07
    ၎
    0.96
    ophilus
    0.95
     francisco
    0.94
     Carré
    0.94
     caña
    0.93
     tafel
    0.92
     vetores
    0.91
    Ещё
    0.90
    Activations Density 0.001%

    No Known Activations