© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2633
    Prev
    Next
    INDEX
    Explanations

    story arcs and events

    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
    noons
    -1.07
    tissimo
    -0.93
    竟然是
    -0.91
     korban
    -0.87
     kreativ
    -0.86
     ibadah
    -0.86
     celebra
    -0.85
    formatics
    -0.84
    itsu
    -0.83
     desenli
    -0.82
    POSITIVE LOGITS
     arc
    1.60
     incident
    1.23
     events
    1.20
     arcs
    1.18
     storyline
    1.12
     battle
    1.09
     tournament
    1.09
     chapter
    1.08
     final
    1.06
     Arc
    1.04
    Activations Density 0.027%

    No Known Activations