© 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. 34-GEMMASCOPE-RES-131K
    7. 76137
    Prev
    Next
    INDEX
    Explanations

    peak or maximum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     堀
    -0.86
    ╲
    -0.82
    ofern
    -0.77
    вих
    -0.77
    ित्र
    -0.75
    ᅮ
    -0.74
     IActionResult
    -0.73
    timmung
    -0.72
     departe
    -0.71
     artig
    -0.71
    POSITIVE LOGITS
     peak
    6.72
    peak
    5.41
    Peak
    5.03
     Peak
    4.91
     peaks
    4.88
     peaked
    4.75
     peaking
    4.44
    peaks
    3.91
     PEAK
    3.86
    ピーク
    3.48
    Activations Density 0.167%

    No Known Activations