© 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. 78729
    Prev
    Next
    INDEX
    Explanations

    Prop Hunt Multiplayer

    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
    🎤
    -0.80
    tensorflow
    -0.76
    🙈
    -0.76
     Warcraft
    -0.75
    ^_^
    -0.73
     dota
    -0.72
     coklat
    -0.72
     ОС
    -0.71
    塞
    -0.70
     lelaki
    -0.70
    POSITIVE LOGITS
     Roblox
    1.13
    Roblox
    1.13
     gui
    0.96
     GUI
    0.94
     Obtain
    0.92
     roblox
    0.91
    Obtain
    0.90
     업
    0.88
     pets
    0.85
     lobby
    0.82
    Activations Density 0.001%

    No Known Activations