© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76979
    Prev
    Next
    INDEX
    Explanations

    precision Partners

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

    speeds, following, sketches

    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
    Not in Any Lists

    No Comments

    Negative Logits
     internes
    0.47
    но
    0.45
    эй
    0.45
    0
    0.45
     sogen
    0.44
    statement
    0.44
    פתח
    0.43
    귤
    0.43
     filoz
    0.43
     indag
    0.43
    POSITIVE LOGITS
     Terr
    0.43
     torn
    0.43
     বিরাট
    0.41
     দ্রুত
    0.41
    ുമ്പോൾ
    0.40
     लहरा
    0.40
     Westfield
    0.40
     নিউ
    0.39
     FEMA
    0.39
     Hudson
    0.39
    Activations Density 0.001%

    No Known Activations