© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 190050
    Prev
    Next
    INDEX
    Explanations

    Russian PROGRAM

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

    minimizing upfront investment

    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
     providers
    0.46
     appe
    0.46
     {.
    0.46
     célé
    0.46
     leiden
    0.46
     mío
    0.44
     پیچھے
    0.44
     NIO
    0.44
     ----
    0.44
     tachy
    0.43
    POSITIVE LOGITS
     Russians
    0.49
    personalized
    0.49
    Russian
    0.48
    PROGRAM
    0.47
    Soviet
    0.46
    罌
    0.46
    METHODS
    0.45
    ucco
    0.45
    stringProp
    0.44
    concat
    0.44
    Activations Density 0.001%

    No Known Activations