© 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. 35307
    Prev
    Next
    INDEX
    Explanations

    following conjunctions and transitions

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

    The neuron activates on numeric tokens (integers or decimals), i.e. it detects 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_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
     кухо
    -0.86
     трубо
    -0.82
     traces
    -0.82
     विष
    -0.80
    теля
    -0.79
    ховик
    -0.76
     agreed
    -0.75
    辛苦
    -0.75
    就是
    -0.73
    娘
    -0.73
    POSITIVE LOGITS
    这句话
    0.96
     interpreted
    0.94
    さの
    0.91
     Applies
    0.91
    înd
    0.90
    ními
    0.90
    Especially
    0.87
     implique
    0.86
    translated
    0.86
     функций
    0.86
    Activations Density 0.093%

    No Known Activations