© 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. 221051
    Prev
    Next
    INDEX
    Explanations

    instructions followed by directives

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

    remove or skip consecutive items

    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
    hline
    0.52
    '][
    0.50
    _{-}$
    0.49
    yscale
    0.49
    _{+}\
    0.48
    iters
    0.48
    monary
    0.47
    ceptions
    0.46
    _{-}^{
    0.45
    _+
    0.44
    POSITIVE LOGITS
     evitar
    0.54
     використання
    0.49
     olmad
    0.49
     kullanıcı
    0.45
    ไม่
    0.45
    き
    0.45
    嫦
    0.45
     rhetoric
    0.45
     không
    0.44
    กระ
    0.44
    Activations Density 0.001%

    No Known Activations