© 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. 71387
    Prev
    Next
    INDEX
    Explanations

    focus or priority

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

    The neuron responds to high-level discourse tokens—common clause- or sentence-boundary markers and intensifiers (e.g. “but,” “I,” “best,” “more,” “rather,” etc.).

    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
    %$$
    -0.91
     почина
    -0.84
     secretions
    -0.82
    Selections
    -0.80
    ार्थ
    -0.79
     Tere
    -0.78
    𝘉
    -0.77
     zarówno
    -0.76
     sultan
    -0.75
     citadel
    -0.74
    POSITIVE LOGITS
     focus
    2.66
    focus
    2.39
    Focus
    2.08
     Focus
    1.85
     focuses
    1.79
     concentrate
    1.70
     focusing
    1.67
     focused
    1.65
     fokus
    1.61
    FOCUS
    1.46
    Activations Density 0.043%

    No Known Activations