© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    job, architecture, shower

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

    The neuron fires on content nouns that occur as part of multi‐word or hyphenated compound noun phrases—e.g. “ground-based,” “day job,” “baby shower,” “Renaissance architecture,” “under card.”

    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
     they
    -1.56
     zunächst
    -1.54
     otras
    -1.42
     gangster
    -1.42
     otros
    -1.41
    灩
    -1.39
     devido
    -1.39
     aufgrund
    -1.36
    commodation
    -1.35
     другие
    -1.34
    POSITIVE LOGITS
     anillos
    1.87
    "
    1.76
     capucha
    1.63
    ;
    1.58
    $
    1.56
    뚠
    1.54
     acabados
    1.50
    '
    1.48
     çantası
    1.47
     defectos
    1.46
    Activations Density 0.082%

    No Known Activations