© 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. 49794
    Prev
    Next
    INDEX
    Explanations

    lump, lumps, lump sum

    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
    ag
    1.63
    ad
    1.62
    w
    1.51
    il
    1.41
    im
    1.38
    c
    1.38
    ip
    1.30
    and
    1.28
    ar
    1.27
    ay
    1.26
    POSITIVE LOGITS
     buildFor
    0.85
    ’
    0.84
     необходимо
    0.82
     оказалось
    0.82
     dlatego
    0.81
     lumped
    0.81
     penyeleng
    0.81
     поэтому
    0.79
     throwIfNotFound
    0.79
    ;
    0.79
    Activations Density 0.004%

    No Known Activations