© 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. 34-GEMMASCOPE-RES-131K
    7. 49065
    Prev
    Next
    INDEX
    Explanations

    numbers following 'ONE' or other number words

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

    The neuron activates on tokens that are multi-digit numbers or number-like codes.

    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
     there
    -1.31
    chaise
    -1.00
    racha
    -0.90
    edith
    -0.88
    orgh
    -0.88
    )),
    -0.88
    roughs
    -0.88
    auda
    -0.88
     предыду
    -0.86
    在这种
    -0.86
    POSITIVE LOGITS
    aneity
    1.12
     still
    1.05
    ance
    1.05
    otropy
    0.94
    今でも
    0.93
    ual
    0.90
    ilty
    0.87
     that
    0.87
    OfWeek
    0.86
    Luis
    0.85
    Activations Density 0.010%

    No Known Activations