© 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. 81800
    Prev
    Next
    INDEX
    Explanations

    Formula 1, company, doors, student

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

    ". (punctuation)

    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
    鳧
    0.51
    תו
    0.49
    킨
    0.49
    참
    0.48
    ással
    0.46
    괜
    0.46
    <unused2146>
    0.46
    ід
    0.46
    არა
    0.46
    +(\
    0.45
    POSITIVE LOGITS
     this
    0.50
     enters
    0.48
    .";
    0.46
    ."
    0.44
     peritoneum
    0.44
     masuk
    0.43
    ....
    0.43
    ...”
    0.43
     Sociology
    0.42
     any
    0.42
    Activations Density 0.000%

    No Known Activations