© 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. 176720
    Prev
    Next
    INDEX
    Explanations

    select, buy, download

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

    mass and energy

    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
     получится
    0.52
    zeitig
    0.50
    žení
    0.48
     końcu
    0.48
    ypi
    0.47
    commodity
    0.47
    ressione
    0.47
    🆙
    0.46
     indústria
    0.45
    tree
    0.44
    POSITIVE LOGITS
    時の
    0.45
    ப்போது
    0.42
    ও
    0.41
    வைத்து
    0.41
     strict
    0.41
    Incorrect
    0.39
    荪
    0.39
    Important
    0.39
     guns
    0.38
    當時
    0.38
    Activations Density 0.001%

    No Known Activations