© 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. 84240
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

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

    This neuron detects numeric literals (tokens consisting 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_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
    Украина
    -1.64
     would
    -1.46
    ･･
    -1.31
    久し
    -1.28
    Elő
    -1.27
    Цена
    -1.27
    ―――
    -1.26
    の人生
    -1.25
    crocs
    -1.23
    Pokud
    -1.23
    POSITIVE LOGITS
    a
    1.44
    *,
    1.41
    e
    1.39
    1.39
    w
    1.30
    *
    1.30
    N
    1.25
    ak
    1.24
    ara
    1.22
    u
    1.22
    Activations Density 0.014%

    No Known Activations