© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49771
    Prev
    Next
    INDEX
    Explanations

    extra copy of chromosome

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     but
    1.00
     with
    0.95
     as
    0.88
     he
    0.85
    de
    0.85
     work
    0.84
     e
    0.81
     and
    0.80
    י
    0.80
     pada
    0.80
    POSITIVE LOGITS
    噦
    0.73
     CBIT
    0.63
    يزات
    0.61
    티브
    0.60
     Стар
    0.59
    ويت
    0.59
     MDET
    0.59
     Prendre
    0.59
    يري
    0.58
    ᱧ
    0.58
    Activations Density 0.000%

    No Known Activations