© 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. 10-GEMMASCOPE-RES-131K
    7. 13992
    Prev
    Next
    INDEX
    Explanations

    aspects of existence and experience

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

    The neuron responds to high-level, abstract content nouns that name broad topics or domains (e.g. life, travel, space, wealth, nature, battle, living).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     for
    -2.94
     also
    -2.19
     then
    -1.96
     which
    -1.95
     now
    -1.94
     in
    -1.91
     or
    -1.72
     so
    -1.68
     where
    -1.65
     related
    -1.65
    POSITIVE LOGITS
     brune
    1.67
     refroid
    1.63
     feront
    1.60
     bascul
    1.60
     condam
    1.57
     vulga
    1.57
     dégust
    1.56
     déclen
    1.55
     ralenti
    1.52
     prét
    1.51
    Activations Density 0.142%

    No Known Activations