© 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. 33668
    Prev
    Next
    INDEX
    Explanations

    derives or draws from

    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
     propre
    -0.91
    более
    -0.85
    Образова
    -0.79
    ратор
    -0.79
    Применение
    -0.79
    ropolitana
    -0.78
     薯
    -0.77
    ueel
    -0.77
    Біо
    -0.76
    uters
    -0.75
    POSITIVE LOGITS
     inspiration
    2.11
     strength
    1.39
     motivation
    1.35
     derive
    1.31
     most
    1.31
     derives
    1.30
    inspiration
    1.29
     cues
    1.26
     its
    1.23
     energy
    1.15
    Activations Density 0.061%

    No Known Activations