© 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. 10-GEMMASCOPE-RES-131K
    7. 8279
    Prev
    Next
    INDEX
    Explanations

    numerical scores and years

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

    The neuron fires on standalone numeric tokens (digits and number sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    锨
    -1.73
    茈
    -1.66
     alſo
    -1.62
     juntamente
    -1.61
    llavero
    -1.57
    
    -1.53
     incluindo
    -1.52
     cuja
    -1.51
    ська
    -1.49
     افرادی
    -1.49
    POSITIVE LOGITS
     first
    2.33
     and
    1.68
     one
    1.65
     every
    1.61
    ."
    1.58
     some
    1.57
     new
    1.51
     because
    1.50
     on
    1.49
     most
    1.41
    Activations Density 0.012%

    No Known Activations