© 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. 99451
    Prev
    Next
    INDEX
    Explanations

    code and document elements

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

    The neuron activates on numeric tokens—sequences of digits such as version numbers, grant IDs, counts, etc.

    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
    ω
    -0.80
    unix
    -0.75
    ør
    -0.74
    requestCode
    -0.71
    Fin
    -0.70
     unix
    -0.70
     Abortion
    -0.70
    UN
    -0.69
    word
    -0.69
    Foot
    -0.69
    POSITIVE LOGITS
    gotta
    0.72
    At
    0.71
    Результа
    0.68
    Fifteen
    0.68
    savings
    0.67
     At
    0.66
    běh
    0.65
    setView
    0.65
    tasty
    0.64
    documentElement
    0.63
    Activations Density 0.639%

    No Known Activations