© 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. 34-GEMMASCOPE-RES-131K
    7. 92790
    Prev
    Next
    INDEX
    Explanations

    literacy and illiteracy

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

    the neuron detects numeric data tokens—especially numbers representing counts, measurements, or statistical figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     teka
    -0.86
     cosplay
    -0.78
    ┖
    -0.72
     apparti
    -0.71
     airsoft
    -0.71
     största
    -0.70
     STRE
    -0.70
    antikan
    -0.70
     bodybuilding
    -0.70
    ORIGINAL
    -0.69
    POSITIVE LOGITS
     literacy
    3.41
     literate
    2.97
     illiterate
    2.80
     Literacy
    2.67
     illiteracy
    2.66
    Literacy
    2.52
    liter
    2.41
     грамо
    1.90
     reading
    1.68
    iteracy
    1.64
    Activations Density 0.019%

    No Known Activations