© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81162
    Prev
    Next
    INDEX
    Explanations

    SDL programming library

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

    The neuron activates on numeric tokens—especially multi‐digit sequences like years, version numbers, and other standalone 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_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
    glMatrix
    -0.80
    Albany
    -0.79
    ESTAMP
    -0.75
    鎗
    -0.75
     Mongo
    -0.71
    τικής
    -0.71
     lysine
    -0.71
    ốn
    -0.70
    HOU
    -0.70
    nologies
    -0.69
    POSITIVE LOGITS
     SDL
    2.20
    SDL
    2.17
     SDLK
    1.23
     Uint
    1.20
    Uint
    1.17
    Sint
    1.12
     Sint
    1.09
    TTF
    1.08
     Massachusetts
    1.05
     SD
    0.97
    Activations Density 0.011%

    No Known Activations