© 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. 65032
    Prev
    Next
    INDEX
    Explanations

    category tag

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

    The neuron detects numeric literals (tokens consisting of digits, often in code paths, attribute values, or version 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
    uje
    -0.83
     steps
    -0.82
     bouts
    -0.80
     molé
    -0.79
     emploi
    -0.77
     jiwa
    -0.76
    ელ
    -0.75
    นี
    -0.73
    publications
    -0.73
     unidos
    -0.71
    POSITIVE LOGITS
     miscellaneous
    2.31
     Miscellaneous
    2.03
    Miscellaneous
    2.02
     misc
    1.89
    misc
    1.76
    MISC
    1.66
     Others
    1.65
    Misc
    1.63
     Misc
    1.60
    Others
    1.50
    Activations Density 0.082%

    No Known Activations