© 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. 10-GEMMASCOPE-RES-131K
    7. 21873
    Prev
    Next
    INDEX
    Explanations

    A1 followed by specific terms

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

    This neuron detects alphanumeric identifier tokens—especially letter-digit codes like “A1” (and similar structured IDs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    阇
    -2.27
    鹮
    -2.16
    鴣
    -2.08
    璆
    -2.06
    rália
    -2.06
    ’
    -1.94
    睺
    -1.94
    ’，
    -1.89
    ggak
    -1.89
    靄
    -1.87
    POSITIVE LOGITS
    In
    2.64
     you
    2.61
    As
    2.44
    [
    2.33
    也
    2.08
     плохо
    2.02
    作为
    2.00
    From
    1.99
    sk
    1.98
    ty
    1.98
    Activations Density 0.012%

    No Known Activations