© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14880
    Prev
    Next
    INDEX
    Explanations

    variable assignment syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ('
    0.41
     hashlib
    0.36
    Ped
    0.35
    uptools
    0.33
    （
    0.33
    ['
    0.33
    必
    0.32
    \[
    0.30
    :\/\/
    0.30
    namespace
    0.30
    POSITIVE LOGITS
    емся
    0.49
    zać
    0.49
     करतो
    0.48
     نحن
    0.48
    gados
    0.46
    ramos
    0.45
    كلمنا
    0.44
     resulta
    0.43
    ümüz
    0.43
    anians
    0.43
    Activations Density 0.075%

    No Known Activations