© 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. 142382
    Prev
    Next
    INDEX
    Explanations

    contemporary textual concerns

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

    narrative conventions

    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
     pd
    0.45
     acetone
    0.44
     Zamb
    0.43
    a
    0.42
     af
    0.42
     triumph
    0.41
    an
    0.41
    as
    0.41
     cup
    0.41
     Py
    0.41
    POSITIVE LOGITS
    führer
    0.50
     લગ
    0.50
    𒉡
    0.49
    বিবাহ
    0.48
     тебя
    0.48
    在你
    0.48
     ಅಥವಾ
    0.48
     نیٹ
    0.48
     クリスマス
    0.47
     消費
    0.47
    Activations Density 0.000%

    No Known Activations