© 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. 92819
    Prev
    Next
    INDEX
    Explanations

    battery life and Western Buddhism

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

    The neuron selectively activates on multi-digit numeric tokens (especially three-digit and larger 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
     lisäksi
    -0.94
     kupić
    -0.91
    Ї
    -0.88
    地看着
    -0.86
     aasta
    -0.85
     valmis
    -0.85
    teca
    -0.85
     robić
    -0.84
    したいと思います
    -0.83
    teile
    -0.82
    POSITIVE LOGITS
    Lors
    0.91
    --){
    0.85
    愛
    0.84
    ..?
    0.82
    lfloor
    0.80
    Tous
    0.80
     desapare
    0.78
     speziellen
    0.78
     Présentation
    0.78
    爱
    0.78
    Activations Density 0.000%

    No Known Activations