© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34129
    Prev
    Next
    INDEX
    Explanations

    job satisfaction of

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

    The neuron responds to the principal topic or key measurement term (e.g. “satisfaction,” “quality of life,” “apoptosis,” “heavy metals,” etc.) that defines the focus of a scientific study.

    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
    词汇
    -1.42
    ところに
    -1.34
    conceito
    -1.30
    ✎
    -1.30
     selaku
    -1.30
     brachte
    -1.29
     Благодаря
    -1.28
    すみません
    -1.25
     cálido
    -1.25
    ISSUE
    -1.23
    POSITIVE LOGITS
     in
    3.44
     with
    2.69
     of
    2.48
     on
    2.47
     for
    2.09
     by
    1.89
    を
    1.73
     at
    1.59
     and
    1.55
    が
    1.34
    Activations Density 0.479%

    No Known Activations