© 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. 27135
    Prev
    Next
    INDEX
    Explanations

    descriptions and details

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

    This neuron fires on numeric tokens—i.e. it detects numbers (integers, decimals, counts) 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
    篇
    -0.84
    玟
    -0.84
     وزار
    -0.82
    IsOptional
    -0.78
    Buongiorno
    -0.78
    нні
    -0.78
     Saison
    -0.76
     facets
    -0.76
    гиоз
    -0.75
    вест
    -0.72
    POSITIVE LOGITS
     Description
    0.89
    Description
    0.88
    着脸
    0.87
     kuhusu
    0.86
    ίες
    0.85
     erz
    0.82
    ịnh
    0.82
    DESCRIPTION
    0.82
    ipment
    0.81
    Actual
    0.80
    Activations Density 0.145%

    No Known Activations