© 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. 22-GEMMASCOPE-RES-131K
    7. 15808
    Prev
    Next
    INDEX
    Explanations

    existence of

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

    This neuron spotlights prominent technical or scientific jargon terms (e.g. specialized nouns in abstracts or descriptions).

    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
     into
    -1.43
     using
    -1.07
    toEqual
    -1.02
     نحو
    -0.98
     about
    -0.95
     głó
    -0.93
    odge
    -0.93
     by
    -0.91
     onto
    -0.89
    into
    -0.86
    POSITIVE LOGITS
     in
    1.27
     във
    1.05
     exists
    0.97
     exist
    0.95
     /\.(
    0.93
     erbjuder
    0.92
     istnieje
    0.90
    
    0.90
    fikation
    0.90
     ở
    0.90
    Activations Density 0.079%

    No Known Activations