© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48515
    Prev
    Next
    INDEX
    Explanations

    false, unique, chlorine, neutral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     الكتاب
    0.45
    ลูกค้า
    0.44
     jakieś
    0.43
     frequently
    0.41
    斯的
    0.41
     epigenetic
    0.41
     Kunden
    0.40
     orthogon
    0.40
    Ꮬ
    0.40
     أشهر
    0.39
    POSITIVE LOGITS
    玛
    0.52
    ar
    0.48
     Domin
    0.48
    ema
    0.46
    utos
    0.46
     dha
    0.46
    χυ
    0.46
     trouve
    0.45
    arie
    0.45
    ely
    0.45
    Activations Density 0.000%

    No Known Activations