© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 10984
    Prev
    Next
    INDEX
    Explanations

    code definition tags

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

    This neuron fires on numeric literal tokens (e.g. standalone numbers) 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
     manger
    -1.02
    ässä
    -0.98
    において
    -0.97
    Specifier
    -0.96
    ellä
    -0.95
    The
    -0.92
    town
    -0.91
    神情
    -0.91
    urfs
    -0.90
    >:
    -0.89
    POSITIVE LOGITS
    なのかな
    1.09
    읽
    1.07
    をお願い
    1.06
    poptotic
    1.05
    為に
    1.02
    іан
    1.01
     always
    0.99
     сути
    0.99
     contactez
    0.98
    높
    0.98
    Activations Density 0.013%

    No Known Activations