© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14737
    Prev
    Next
    INDEX
    Explanations

    success and awesome evaluations

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

    This neuron responds strongly to celebratory or congratulatory language announcing successes—especially the word “success” and related positive, achievement-oriented terms.

    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
     in
    -1.89
     currently
    -1.66
     now
    -1.41
     Recently
    -1.34
     then
    -1.31
     Currently
    -1.28
     When
    -1.24
    已
    -1.21
    ђу
    -1.21
    已经
    -1.21
    POSITIVE LOGITS
     was
    1.77
    かったです
    1.58
     homoto
    1.36
     everyone
    1.34
    事前に
    1.34
     attendance
    1.31
     ήταν
    1.30
    もあった
    1.27
     territo
    1.27
     많은
    1.25
    Activations Density 0.038%

    No Known Activations