© 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. 4729
    Prev
    Next
    INDEX
    Explanations

    changes in

    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
     are
    0.92
    ،
    0.80
    4
    0.77
    that
    0.74
     لیکن
    0.72
    5
    0.71
    igh
    0.71
    atch
    0.67
    ی
    0.67
    いますが
    0.65
    POSITIVE LOGITS
    h
    1.23
    ر
    1.16
    o
    1.09
    is
    1.09
    n
    1.08
    r
    1.03
    y
    1.03
    et
    1.02
    на
    0.94
    en
    0.93
    Activations Density 0.066%

    No Known Activations