© 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. 42884
    Prev
    Next
    INDEX
    Explanations

    desired Costco Ham

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

    action types

    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
    äten
    0.51
     اقت
    0.49
     categoryService
    0.49
    ören
    0.49
    妵
    0.49
    ardır
    0.48
    ení
    0.48
     figyel
    0.48
    ména
    0.47
    öre
    0.47
    POSITIVE LOGITS
    ມັນ
    0.50
    H
    0.50
    A
    0.49
    Women
    0.49
     Bounds
    0.47
    ,),
    0.46
     playoffs
    0.46
    )—
    0.45
    ,]
    0.45
    子ども
    0.44
    Activations Density 0.000%

    No Known Activations