© 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. 123718
    Prev
    Next
    INDEX
    Explanations

    same time

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

    creating stories and sequences

    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
     {
    0.58
     as
    0.54
     கொண்டு
    0.51
     reports
    0.48
    âu
    0.48
     a
    0.48
    plement
    0.48
     and
    0.47
    ồi
    0.47
    년간
    0.46
    POSITIVE LOGITS
     उत्साहित
    0.51
     zvuk
    0.48
     മുഴ
    0.48
    товая
    0.46
    <unused39>
    0.45
     ध्वनि
    0.45
     liquide
    0.45
     Fateh
    0.45
     डेफिनेशन
    0.44
    వృద్ధి
    0.44
    Activations Density 0.000%

    No Known Activations