© 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. 38451
    Prev
    Next
    INDEX
    Explanations

    categories and lists

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

    The neuron activates on numeric tokens that appear as counts or indices in list‐style expressions.

    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
    ystemet
    -0.99
    тт
    -0.96
     وجود
    -0.95
     komplette
    -0.94
    lero
    -0.94
     hébergement
    -0.92
     eyeballs
    -0.91
    ĝ
    -0.90
    utiful
    -0.90
     frein
    -0.90
    POSITIVE LOGITS
     other
    1.38
     those
    1.36
     others
    1.22
     of
    1.16
     because
    1.14
     list
    1.09
     where
    1.07
     group
    1.07
     highly
    1.06
     few
    1.04
    Activations Density 0.096%

    No Known Activations