© 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. 27116
    Prev
    Next
    INDEX
    Explanations

    founder and title

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

    The neuron strongly activates on standalone numeric tokens (e.g. years or other multi-digit 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_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
     diversos
    -1.26
    うーん
    -1.23
     både
    -1.22
    Kör
    -1.22
    盦
    -1.20
    ability
    -1.20
    骉
    -1.18
    aneity
    -1.18
    ཌ
    -1.18
     algún
    -1.17
    POSITIVE LOGITS
     of
    1.77
     in
    1.21
     a
    1.12
     tirantes
    1.07
     chief
    1.07
    '
    1.06
     lifelong
    1.05
     Chief
    1.03
     ‘
    1.02
     cerveau
    1.00
    Activations Density 0.029%

    No Known Activations