© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    scavenger hunt, documentary, race

    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
     dissect
    -0.76
     annexation
    -0.74
     Mock
    -0.73
    胚
    -0.72
     mockup
    -0.71
     variegated
    -0.71
     thermoplastic
    -0.70
     mock
    -0.69
     guardianship
    -0.69
     jew
    -0.68
    POSITIVE LOGITS
     teams
    1.15
     eliminated
    1.06
    Teams
    1.05
    teams
    0.96
     Race
    0.96
     legs
    0.94
     TAR
    0.91
     Reichen
    0.90
     racers
    0.90
     equipos
    0.90
    Activations Density 0.006%

    No Known Activations