© 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. 108838
    Prev
    Next
    INDEX
    Explanations

    packaging, paint, work, tree, site

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

    avoiding negative outcomes

    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
     CONTRIBUTORS
    0.51
    adians
    0.45
    iin
    0.43
     கூடிய
    0.43
    anes
    0.42
     বিএনপির
    0.42
    sourceIP
    0.42
    &*
    0.41
    மம்
    0.41
     Republicans
    0.41
    POSITIVE LOGITS
     refract
    0.48
    jourd
    0.46
    崔
    0.46
     perror
    0.44
    ιδ
    0.44
    ణ
    0.44
    رد
    0.43
    heureusement
    0.43
    рно
    0.43
    लेशन
    0.42
    Activations Density 0.000%

    No Known Activations