© 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. 117449
    Prev
    Next
    INDEX
    Explanations

    My story

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

    The neuron activates on sequences of digits (numeric literals) in the code.

    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
    くださいませ
    -1.03
    livé
    -0.89
    욱
    -0.88
     quae
    -0.83
    渍
    -0.82
    흥
    -0.82
    Ќ
    -0.80
     bättre
    -0.80
    全球
    -0.79
    grà
    -0.79
    POSITIVE LOGITS
    IDK
    0.85
     protocolos
    0.80
     dirname
    0.79
     CHAPITRE
    0.77
     Coim
    0.77
     fuff
    0.77
    ള്
    0.74
     periodical
    0.73
    ートル
    0.73
    BottomSheet
    0.73
    Activations Density 0.001%

    No Known Activations