© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197803
    Prev
    Next
    INDEX
    Explanations

    countries travelling to Arabia

    np_acts-logits-general · gemini-2.5-flash-lite

    production status explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    我
    0.52
    ')])
    0.50
     BOARDSIZE
    0.50
    平台上
    0.50
    ها
    0.49
    气
    0.48
    COOH
    0.47
    两
    0.46
    就
    0.45
    上前
    0.45
    POSITIVE LOGITS
     decommission
    0.50
     todays
    0.46
     Kom
    0.45
     heutigen
    0.45
     blockade
    0.44
     provoking
    0.44
     contagion
    0.43
     Sala
    0.43
    ੋਰ
    0.42
     damaging
    0.42
    Activations Density 0.001%

    No Known Activations