© 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. 71413
    Prev
    Next
    INDEX
    Explanations

    folder or state names

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

    The neuron selectively activates on tokens containing digits (i.e. numeric literals or subscript 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
    pecified
    -0.90
     Hälfte
    -0.89
    czech
    -0.88
     then
    -0.85
     at
    -0.84
    enfone
    -0.82
    したので
    -0.82
     Because
    -0.82
    lidays
    -0.81
     because
    -0.80
    POSITIVE LOGITS
    engesch
    0.90
     Suche
    0.90
     masing
    0.89
    StrictEqual
    0.89
     arn
    0.88
    each
    0.86
     hikariConfig
    0.84
    mathcal
    0.82
    킁
    0.80
    gráfico
    0.80
    Activations Density 0.029%

    No Known Activations