© 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. 178544
    Prev
    Next
    INDEX
    Explanations

    final piece

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

    financial and medical terms

    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
    akum
    0.60
    akrishnan
    0.55
    acağız
    0.54
    ейчас
    0.52
    kum
    0.51
    ekom
    0.51
    បំ
    0.51
    cevam
    0.51
    érrez
    0.49
    𝟭
    0.49
    POSITIVE LOGITS
    ’
    0.52
    ).
    0.48
    $).
    0.47
    The
    0.46
     barre
    0.45
    Introducing
    0.44
    \(
    0.42
    ,“
    0.42
    PI
    0.42
    the
    0.41
    Activations Density 0.000%

    No Known Activations