© 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. 245807
    Prev
    Next
    INDEX
    Explanations

    requested newsletter

    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
    ano
    0.47
    oos
    0.46
    SEQU
    0.46
     Bukan
    0.46
     LETTERS
    0.46
     CONNECT
    0.45
    oop
    0.45
     ন
    0.44
     plupart
    0.44
     Conrad
    0.43
    POSITIVE LOGITS
    حة
    0.51
    爣
    0.48
    ادت
    0.48
    şiv
    0.47
    بر
    0.47
     tensione
    0.45
     fût
    0.44
    நபியே
    0.44
    تحانات
    0.43
    兹
    0.43
    Activations Density 0.002%

    No Known Activations