© 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. 34-GEMMASCOPE-RES-131K
    7. 103335
    Prev
    Next
    INDEX
    Explanations

    citation markers and dollar sign endings

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

    The neuron responds to numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     alimentaria
    -0.81
     pięk
    -0.76
    ごち
    -0.75
     escenario
    -0.74
     Rohr
    -0.73
    SuccessListener
    -0.73
     Collingwood
    -0.72
    前进
    -0.71
    thenReturn
    -0.71
    itag
    -0.71
    POSITIVE LOGITS
    મે
    0.70
    箏
    0.70
     borde
    0.69
    ֵל
    0.68
     Keller
    0.67
    ære
    0.66
     Freud
    0.66
    Ay
    0.66
     guida
    0.66
    спор
    0.65
    Activations Density 0.039%

    No Known Activations