© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152878
    Prev
    Next
    INDEX
    Explanations

    data version privacy cases

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

    research overview

    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
    Negative Logits
     déplacements
    0.46
     arom
    0.45
    udrait
    0.44
     replace
    0.44
     covalent
    0.43
    ಕರಣ
    0.43
     synd
    0.43
     produt
    0.43
     ተ
    0.43
     directive
    0.43
    POSITIVE LOGITS
    amid
    0.57
    raining
    0.50
    ayment
    0.47
    ૬
    0.44
    query
    0.44
     спраши
    0.44
    5
    0.44
    ５
    0.44
    delimiter
    0.44
    ６
    0.44
    Activations Density 0.001%

    No Known Activations