© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38857
    Prev
    Next
    INDEX
    Explanations

    Here we report

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

    This neuron selectively activates on numeric tokens (e.g. measures, percentages, citation numbers), essentially spotting any sequence of digits.

    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
     rekom
    -1.13
     grafik
    -1.07
    teknik
    -1.06
    鳊
    -1.05
    )):
    -1.05
    栳
    -1.03
    仅
    -1.02
    ็อ
    -1.02
    ]):
    -1.01
    MultipartFile
    -1.00
    POSITIVE LOGITS
    uegos
    1.09
     sanitarios
    1.01
    waiting
    1.01
     แต
    0.99
     acessar
    0.98
    link
    0.96
    arthed
    0.94
     nacionales
    0.94
     ativar
    0.93
    ,
    0.93
    Activations Density 0.045%

    No Known Activations