© 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. 129664
    Prev
    Next
    INDEX
    Explanations

    figured out

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

    version control and collaboration

    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
    一
    0.45
    де
    0.44
    ঘরে
    0.44
    第一
    0.42
     facebook
    0.42
    ре
    0.42
    וה
    0.42
    ("/");
    0.41
    （
    0.41
    萨
    0.41
    POSITIVE LOGITS
     numerosi
    0.52
     nisk
    0.52
     کم
    0.51
    StarObject
    0.51
    centage
    0.51
     savaş
    0.51
     arası
    0.50
    quirements
    0.50
     gençler
    0.50
     یقین
    0.49
    Activations Density 0.000%

    No Known Activations