© 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. 38726
    Prev
    Next
    INDEX
    Explanations

    's and contractions

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

    The neuron activates on numeric tokens (digits, years, and numeric hyphenated sequences).

    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
    oplasts
    -0.91
    aways
    -0.91
     Dogg
    -0.79
     mène
    -0.79
    นี
    -0.79
    moires
    -0.79
     funcion
    -0.74
     versión
    -0.74
     in
    -0.74
     so
    -0.73
    POSITIVE LOGITS
    タル
    1.00
     your
    0.90
     ornamented
    0.85
     beż
    0.85
     embodi
    0.85
    ⴽ
    0.84
    ཻ
    0.84
     qashqai
    0.83
    orna
    0.83
    ipt
    0.82
    Activations Density 0.005%

    No Known Activations