© 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. 77148
    Prev
    Next
    INDEX
    Explanations

    visiting graves, drivers, designated bishops

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

    The neuron strongly activates on numeric tokens (digits), i.e. it detects numbers—including years, versions, and other numeric values.

    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
     SIGNATURE
    -0.73
    icali
    -0.73
     セール
    -0.71
    uelva
    -0.71
    illard
    -0.69
     كبير
    -0.69
     CHIN
    -0.68
     warszawa
    -0.68
    꼈
    -0.66
     Radeon
    -0.66
    POSITIVE LOGITS
     Visiting
    0.69
     来
    0.68
     Designated
    0.67
     Podcasts
    0.63
     Positive
    0.63
    Visiting
    0.63
     совмести
    0.63
     Pole
    0.63
     VII
    0.62
     defin
    0.61
    Activations Density 0.064%

    No Known Activations