© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10501
    Prev
    Next
    INDEX
    Explanations

    \[[@...\]\]

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

    The neuron detects numeric reference markers (i.e. citation or footnote 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_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
     will
    -2.78
     of
    -2.59
     only
    -2.44
     from
    -2.41
     first
    -2.38
     and
    -2.33
     in
    -2.31
     When
    -2.27
     created
    -2.25
     creates
    -2.16
    POSITIVE LOGITS
     zoude
    2.27
     rése
    2.23
    ;</
    2.19
     pérd
    2.16
     Dinas
    2.11
    轳
    2.06
    螃
    2.06
    呶
    2.05
     kado
    2.05
    quelles
    2.05
    Activations Density 0.012%

    No Known Activations