© 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. 67454
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron activates on numeric tokens (including integers and decimals), i.e. whenever a measurement, dosage, count, or other number appears 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
     rudimentary
    -0.97
    感兴趣
    -0.83
    inities
    -0.83
     restricting
    -0.83
    ֳ
    -0.80
    也可以
    -0.79
     useAuth
    -0.78
    ronom
    -0.76
     this
    -0.76
    ubarak
    -0.75
    POSITIVE LOGITS
     財布
    0.90
     frança
    0.86
     детской
    0.85
     детские
    0.82
     детских
    0.80
    反而
    0.78
    used
    0.75
     первые
    0.75
    得罪
    0.75
     getroffen
    0.74
    Activations Density 0.370%

    No Known Activations