© 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. 92320
    Prev
    Next
    INDEX
    Explanations

    hotel deals and car rentals

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

    DM and guidelines

    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
    irdiği
    0.47
    ᱡ
    0.44
    த்துப்
    0.43
    trä
    0.42
    ровень
    0.39
     Donna
    0.39
    isDirectory
    0.39
    łem
    0.39
    ሷ
    0.38
    getPrice
    0.38
    POSITIVE LOGITS
    dm
    0.46
     outpouring
    0.44
    DM
    0.44
     incubator
    0.43
     waterslide
    0.42
     encircled
    0.42
     tracks
    0.41
     dm
    0.41
    Stamped
    0.41
    smt
    0.40
    Activations Density 0.001%

    No Known Activations