© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92791
    Prev
    Next
    INDEX
    Explanations

    menu and food titles

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

    The neuron fires on the “+” addition symbol (in numeric or arithmetic 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_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
    ℡
    -0.96
     lyder
    -0.96
     from
    -0.93
     Because
    -0.91
     because
    -0.91
     after
    -0.88
    pēc
    -0.87
     revital
    -0.87
     häm
    -0.86
     epitom
    -0.85
    POSITIVE LOGITS
    踉
    0.94
    mostly
    0.90
    ai
    0.88
    topes
    0.88
     momentous
    0.84
    踌
    0.83
    osphere
    0.80
    imo
    0.79
     Dinas
    0.79
     molti
    0.79
    Activations Density 0.000%

    No Known Activations