© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91334
    Prev
    Next
    INDEX
    Explanations

    web attributes and tags

    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
    Bloomberg
    -0.76
    scanf
    -0.75
    render
    -0.75
    Florida
    -0.74
    kheim
    -0.72
    Tender
    -0.71
     ته
    -0.71
    ynen
    -0.71
     фай
    -0.70
    тли
    -0.70
    POSITIVE LOGITS
    ISSUE
    0.98
     Chairs
    0.94
    ביר
    0.88
    nejšie
    0.87
     chairs
    0.83
     ARIA
    0.83
    Zak
    0.82
     ஊ
    0.81
     techniques
    0.80
     formaggio
    0.80
    Activations Density 0.086%

    No Known Activations