© 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. 59225
    Prev
    Next
    INDEX
    Explanations

    Wagyu beef, pull the trigger, the Americas

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

    what is eaten

    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
    வெளி
    0.54
    Ⲗ
    0.53
    తో
    0.52
     खूबसूरती
    0.50
    빛
    0.49
    Liste
    0.49
    überküloz
    0.48
     growers
    0.48
    ாளர்களுக்கு
    0.48
    iyoruz
    0.47
    POSITIVE LOGITS
    n
    0.50
    on
    0.49
     legen
    0.49
    s
    0.48
    )
    0.48
    is
    0.45
    p
    0.45
    d
    0.44
    van
    0.44
    o
    0.44
    Activations Density 0.000%

    No Known Activations