© 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. 35498
    Prev
    Next
    INDEX
    Explanations

    partners, conversational, sex

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

    The main thing this neuron does is find numeric tokens (sequences of digits) 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
    labelControl
    -0.88
    を実施
    -0.86
     endeavour
    -0.85
     musiciens
    -0.82
    उत्तर
    -0.81
    unicaciones
    -0.81
    ană
    -0.80
    rió
    -0.77
     prenez
    -0.77
     obje
    -0.77
    POSITIVE LOGITS
     acclaimed
    0.93
    磋
    0.92
     majeurs
    0.91
     ۱۳
    0.87
     MASTER
    0.81
    łom
    0.81
     BEGINNING
    0.81
     SEVER
    0.81
     plusieurs
    0.80
    又能
    0.79
    Activations Density 0.024%

    No Known Activations