© 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. 27642
    Prev
    Next
    INDEX
    Explanations

    Physical Review journal citations

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

    numerical codes and classifications

    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
    buying
    0.46
    吃飯
    0.45
    bought
    0.45
     আটক
    0.43
    夏の
    0.43
     satın
    0.42
     বিদ্য
    0.41
    驚
    0.41
    summer
    0.41
    commission
    0.41
    POSITIVE LOGITS
     கதா
    0.46
     antire
    0.45
     varnish
    0.42
     ($\
    0.41
     ${\
    0.41
    ittää
    0.41
     physics
    0.41
     setzt
    0.41
     sub
    0.40
    Numerical
    0.40
    Activations Density 0.000%

    No Known Activations