© 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. 98874
    Prev
    Next
    INDEX
    Explanations

    Victoria's Secret catwalks

    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
    ⓖ
    -0.90
     Krum
    -0.88
    كال
    -0.78
     Institu
    -0.78
     Wiesen
    -0.78
    WBC
    -0.76
     parcela
    -0.75
    arnas
    -0.74
     keputusan
    -0.73
    个月
    -0.73
    POSITIVE LOGITS
    ėl
    0.77
    🦮
    0.73
     wastewater
    0.71
     border
    0.70
    ximation
    0.70
     Delta
    0.69
    DATETIME
    0.69
    ">#
    0.69
    陽
    0.69
     Victoria
    0.68
    Activations Density 0.000%

    No Known Activations