© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128459
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find numeric tokens (numbers and number-like strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    conjunctions and negations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ть
    -0.84
     Halen
    -0.83
    hicles
    -0.83
     metav
    -0.82
     notamment
    -0.81
    🄲
    -0.81
     CLAY
    -0.80
     Steiner
    -0.80
     morts
    -0.79
    𓆉
    -0.79
    POSITIVE LOGITS
     because
    1.34
    because
    1.17
    Because
    1.05
     благодаря
    1.01
     will
    1.00
     their
    0.93
     due
    0.93
     knows
    0.89
     检查
    0.88
     Because
    0.87
    Activations Density 0.047%

    No Known Activations