© 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. 47727
    Prev
    Next
    INDEX
    Explanations

    Dragon ball, boat, china, fly

    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
    動物
    -1.02
    ętr
    -0.97
     osten
    -0.88
    ,:
    -0.88
    这家伙
    -0.85
    使い方
    -0.84
    动物
    -0.84
     Avian
    -0.82
     Supervisory
    -0.81
    襬
    -0.81
    POSITIVE LOGITS
    🐉
    1.52
    🐲
    1.31
    flies
    1.21
    breath
    1.06
    fly
    1.05
     slayer
    1.01
     Dragons
    0.94
     Slayer
    0.93
    Dragons
    0.89
    FLY
    0.86
    Activations Density 0.005%

    No Known Activations