© 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. 22-GEMMASCOPE-RES-131K
    7. 109
    Prev
    Next
    INDEX
    Explanations

    UI structure elements like legends and panels

    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_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
    aptation
    -0.92
    ᾴ
    -0.91
    $\$$
    -0.90
     to
    -0.89
     링
    -0.89
    らす
    -0.86
     who
    -0.85
     plagio
    -0.85
    ⸨
    -0.84
    rono
    -0.83
    POSITIVE LOGITS
     enclosure
    1.16
    ὺς
    1.12
     titled
    1.01
     съм
    1.00
     invá
    0.97
    貧
    0.96
     SQLException
    0.95
     visites
    0.94
    хіво
    0.94
    Nhap
    0.94
    Activations Density 0.002%

    No Known Activations