© 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. 237896
    Prev
    Next
    INDEX
    Explanations

    mail address

    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
     Affairs
    0.48
    &=
    0.48
    kak
    0.44
    kon
    0.43
    ise
    0.43
    "),
    0.43
     Additionally
    0.43
    agt
    0.43
    &-
    0.43
    |=
    0.42
    POSITIVE LOGITS
    лі
    0.55
    лім
    0.54
    룀
    0.53
    他们的
    0.53
    他們的
    0.53
    лів
    0.51
    컴
    0.50
    ुलम
    0.49
    П
    0.49
    рып
    0.48
    Activations Density 0.001%

    No Known Activations