© 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. 46240
    Prev
    Next
    INDEX
    Explanations

    of creation and results

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

    arrays for issue

    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
     प्रशास
    0.46
    функ
    0.46
    ‌پ
    0.45
    此前
    0.45
     இதுவரை
    0.45
    менова
    0.44
    Parliament
    0.43
     недалеко
    0.43
    疟
    0.43
    VICES
    0.43
    POSITIVE LOGITS
     defendants
    0.48
    oriented
    0.46
     oriented
    0.44
     conglomerates
    0.43
     fidget
    0.41
     Moms
    0.41
     Lastly
    0.40
     reputations
    0.40
    kitt
    0.40
     themed
    0.40
    Activations Density 0.000%

    No Known Activations