© 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. 60594
    Prev
    Next
    INDEX
    Explanations

    narrative fiction

    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
    アシ
    -0.77
    CDCl
    -0.77
    ğum
    -0.76
    "][
    -0.76
    クレ
    -0.76
    cisive
    -0.75
     insights
    -0.74
    estones
    -0.73
    žd
    -0.73
     каса
    -0.73
    POSITIVE LOGITS
     die
    1.55
    die
    1.25
     DIE
    1.13
    Die
    1.05
     fictional
    0.98
     fiction
    0.94
    DIE
    0.93
     narrative
    0.90
     diete
    0.86
     represented
    0.85
    Activations Density 0.017%

    No Known Activations