© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117867
    Prev
    Next
    INDEX
    Explanations

    single grid

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

    The neuron is strongly activated by numbers (digits and counts) and other high-frequency “list” or function tokens (common articles, conjunctions, punctuation) that typically appear in enumerations or feature‐lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    quées
    -0.84
    ꦿ
    -0.74
    ЗУ
    -0.73
    verwaltung
    -0.73
    хани
    -0.72
     jadx
    -0.72
     tämän
    -0.71
     zien
    -0.71
     Decorating
    -0.71
    ilidade
    -0.71
    POSITIVE LOGITS
     single
    1.06
    single
    1.03
     Grid
    0.99
     Single
    0.93
     GRID
    0.93
    Single
    0.92
    SINGLE
    0.91
     grid
    0.88
     SINGLE
    0.86
     blog
    0.84
    Activations Density 0.010%

    No Known Activations