© 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. 54043
    Prev
    Next
    INDEX
    Explanations

    arithmetic expressions and code structures

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

    The neuron is selectively activating on numeric literals (tokens representing numbers).

    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
     usando
    -0.86
     menit
    -0.85
     SECOND
    -0.85
     mesta
    -0.84
     adev
    -0.84
     supli
    -0.83
     palestra
    -0.82
    ”،
    -0.82
     fecond
    -0.82
     hrd
    -0.81
    POSITIVE LOGITS
    感覚
    0.82
     in
    0.81
     Lov
    0.77
     did
    0.74
    ïc
    0.73
    ⅕
    0.72
    Lov
    0.71
     around
    0.71
     vandens
    0.71
     from
    0.71
    Activations Density 0.058%

    No Known Activations