© 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. 106932
    Prev
    Next
    INDEX
    Explanations

    content and package names

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

    The neuron strongly activates on standalone numeric tokens (digits and numbers).

    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
    yasi
    -0.87
    ají
    -0.76
    uves
    -0.76
    Buck
    -0.74
    WAII
    -0.73
     enkelte
    -0.73
    riti
    -0.72
    orino
    -0.71
    petit
    -0.70
    mouseover
    -0.69
    POSITIVE LOGITS
    illo
    0.66
     fantasies
    0.65
    ïne
    0.63
    順位
    0.63
     tersangka
    0.62
    至此
    0.62
    éna
    0.61
    老爷子
    0.60
     отъ
    0.60
    illos
    0.60
    Activations Density 0.052%

    No Known Activations