© 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. 49549
    Prev
    Next
    INDEX
    Explanations

    Quake Unreal games

    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
    Mole
    -0.80
     mole
    -0.77
     unsigned
    -0.74
     Studio
    -0.73
     ۲۰۱
    -0.73
     tin
    -0.72
     dau
    -0.72
    蛤
    -0.69
     factored
    -0.69
     Daw
    -0.68
    POSITIVE LOGITS
    istical
    0.86
    вѣ
    0.82
     Quake
    0.81
    ︷
    0.80
     Unreal
    0.78
     AAS
    0.78
     bicchiere
    0.77
     Envy
    0.77
    Unreal
    0.77
    ėti
    0.76
    Activations Density 0.022%

    No Known Activations