© 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. 174535
    Prev
    Next
    INDEX
    Explanations

    biosimilars

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

    weekend, effects, stationary

    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
     *:
    0.53
    :
    0.53
    ={{
    0.52
     rece
    0.51
    ::
    0.50
     Waffen
    0.48
     fom
    0.48
     I
    0.48
    <sub>
    0.47
     lendemain
    0.47
    POSITIVE LOGITS
    नी
    0.48
    ुआ
    0.48
    تحانات
    0.47
     untrue
    0.46
     большое
    0.46
     baths
    0.45
    ुक
    0.45
    ೃಷ್ಣ
    0.45
    ज
    0.45
    Lim
    0.45
    Activations Density 0.002%

    No Known Activations