© 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. 26138
    Prev
    Next
    INDEX
    Explanations

    citation markers

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

    The neuron responds to numeric digits (0–9) embedded in programming identifiers or code tokens.

    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
     garrafa
    -1.20
     Könige
    -1.12
    贻
    -1.11
     damskie
    -1.09
    ďaka
    -1.08
     damski
    -1.07
     caminhada
    -1.05
    蛤
    -1.05
    頂いた
    -1.02
    今天的
    -1.01
    POSITIVE LOGITS
    d
    1.13
    new
    1.12
    e
    1.03
    j
    1.02
    (),
    1.02
    ($"
    1.02
    even
    1.01
     to
    1.00
    _
    0.94
    ).
    0.93
    Activations Density 0.004%

    No Known Activations