© 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. 22-GEMMASCOPE-RES-131K
    7. 35239
    Prev
    Next
    INDEX
    Explanations

    Introduction, Home, design, Name

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

    The neuron fires on any token containing numeric digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     hjemmeside
    -1.10
     españa
    -1.06
     dinoss
    -1.02
     forskning
    -1.01
     frigo
    -1.00
     portugu
    -0.99
     londres
    -0.98
     yogur
    -0.98
     espet
    -0.97
     AÑOS
    -0.96
    POSITIVE LOGITS
    isition
    1.00
     keperluan
    0.99
     besoins
    0.97
    ανα
    0.97
    tainen
    0.96
     poussière
    0.93
     ohnehin
    0.93
     ModelExpression
    0.91
    これも
    0.91
    ience
    0.90
    Activations Density 0.001%

    No Known Activations