© 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. 31-GEMMASCOPE-2-RES-262K
    7. 109461
    Prev
    Next
    INDEX
    Explanations

    contrast or change

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    st
    0.49
     we
    0.49
    sen
    0.49
     liberation
    0.48
     mistake
    0.47
    ston
    0.45
    s
    0.45
    we
    0.45
     another
    0.44
    ve
    0.44
    POSITIVE LOGITS
    ологии
    0.53
     płyt
    0.53
     ktorá
    0.47
    鼓励
    0.47
    <unused44>
    0.46
    ත්ම
    0.46
     சுத்த
    0.46
    граммы
    0.45
     которая
    0.44
     która
    0.44
    Activations Density 0.001%

    No Known Activations