© 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. 212698
    Prev
    Next
    INDEX
    Explanations

    links and navigation

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

    specific attack

    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
     acrescent
    0.48
    ाने
    0.48
    上が
    0.46
     اضافہ
    0.46
    맺
    0.46
     has
    0.45
     naik
    0.45
     worsened
    0.45
     казни
    0.44
     tampoco
    0.44
    POSITIVE LOGITS
    ó
    0.47
     curate
    0.43
    llr
    0.42
    software
    0.42
     navigation
    0.41
    ng
    0.40
    switch
    0.40
     elec
    0.40
     doors
    0.40
     عارفين
    0.40
    Activations Density 0.001%

    No Known Activations