© 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. 81001
    Prev
    Next
    INDEX
    Explanations

    variable assignment using =

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

    The neuron fires on single‐letter identifiers (like x, y, z, q, g, etc.) used as variables in math formulas.

    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
    igshid
    -0.96
    最重要的
    -0.91
    的人生
    -0.87
     Sollte
    -0.86
     дело
    -0.86
    olverine
    -0.85
    ｐ
    -0.84
     others
    -0.84
     attacco
    -0.83
     something
    -0.82
    POSITIVE LOGITS
     =
    1.51
    =
    1.33
     = 
    1.06
     Є
    1.01
    Calif
    1.00
    Ď
    1.00
     peluche
    1.00
    <sub>
    0.99
    шите
    0.95
    ätie
    0.95
    Activations Density 0.223%

    No Known Activations