© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108384
    Prev
    Next
    INDEX
    Explanations

    team names

    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
     WL
    -0.82
    icamente
    -0.79
     toiture
    -0.77
     Kuma
    -0.75
     KU
    -0.74
     Uta
    -0.74
     Urea
    -0.73
     superman
    -0.73
     Amman
    -0.72
     computing
    -0.71
    POSITIVE LOGITS
     team
    2.55
     teams
    2.28
    team
    2.19
    Team
    1.86
    teams
    1.82
     Team
    1.80
     tag
    1.65
    Teams
    1.65
    getTeam
    1.61
     Teams
    1.52
    Activations Density 0.005%

    No Known Activations