© 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. 10-GEMMASCOPE-RES-131K
    7. 3883
    Prev
    Next
    INDEX
    Explanations

    shadow, shadowing, Shadow Cabinet

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

    This neuron fires on specialized jargon terms—complex, multi-syllable words built from Latin/Greek roots (e.g. “shadowing,” “informal,” “pseudoaneurysm,” “reposync”).

    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
     praktische
    -1.63
     mehreren
    -1.47
     probablement
    -1.45
     gefe
    -1.45
     mediocre
    -1.45
     plusieurs
    -1.44
     Dinas
    -1.38
    boleh
    -1.38
     luscious
    -1.37
     někdo
    -1.37
    POSITIVE LOGITS
    D
    1.57
    S
    1.56
    G
    1.49
     because
    1.48
    Y
    1.44
    F
    1.43
    J
    1.42
    C
    1.41
    N
    1.31
     Because
    1.30
    Activations Density 0.020%

    No Known Activations