© 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. 108641
    Prev
    Next
    INDEX
    Explanations

    morning reality orders dome

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

    abstraction

    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
     النهايات
    0.49
     sulfates
    0.49
     الهم
    0.48
     bushings
    0.46
     Eternity
    0.45
     piers
    0.45
    汽
    0.45
    ご連絡
    0.44
     substrings
    0.44
     Geet
    0.43
    POSITIVE LOGITS
    as
    0.54
    una
    0.49
    asida
    0.48
    ard
    0.46
     relativo
    0.45
    inde
    0.45
    ec
    0.44
     birinci
    0.44
    🎲
    0.43
     Millennium
    0.43
    Activations Density 0.001%

    No Known Activations