© 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. 43268
    Prev
    Next
    INDEX
    Explanations

    numbers and article identifiers

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

    mathematical operations and dates

    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
     covariance
    0.54
    ;\;\
    0.48
    ();
    0.43
     गण
    0.42
     stalled
    0.42
     criminally
    0.42
    ড়যন্ত্র
    0.42
    ErrorReport
    0.41
    ()));
    0.40
    Manager
    0.40
    POSITIVE LOGITS
     Logos
    0.46
     odpowied
    0.45
     reinterpret
    0.45
    ھی
    0.42
     selain
    0.42
     Its
    0.39
     الب
    0.39
     اپنی
    0.39
    selves
    0.38
     ilmu
    0.38
    Activations Density 0.000%

    No Known Activations