© 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. 34979
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron strongly activates on numeric tokens (years, ages, measurements, decimals, 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_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
    兩
    -1.08
    مقال
    -1.06
    金
    -1.00
    ข่าว
    -0.99
     Gehalt
    -0.98
    錚
    -0.98
     확인함
    -0.97
    Komentar
    -0.93
     unei
    -0.93
    🗂
    -0.91
    POSITIVE LOGITS
    ...
    1.05
     mineures
    0.93
    ".
    0.90
     présentes
    0.90
     Mitgliedern
    0.90
    im
    0.88
     niečo
    0.86
    跑去
    0.86
     sammeln
    0.86
    ina
    0.86
    Activations Density 0.043%

    No Known Activations