© 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. 45672
    Prev
    Next
    INDEX
    Explanations

    plot and story

    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
    ariato
    -0.79
    ſo
    -0.76
     piemē
    -0.75
     pembaca
    -0.73
    rā
    -0.70
    áculos
    -0.70
    čnega
    -0.69
    ereço
    -0.69
    ajat
    -0.69
     性感
    -0.68
    POSITIVE LOGITS
     plot
    5.53
     storyline
    4.91
     story
    4.69
    plot
    4.22
     сюжет
    3.84
     plots
    3.81
     Plot
    3.70
     storylines
    3.66
    Plot
    3.64
    story
    3.39
    Activations Density 0.102%

    No Known Activations