© 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. 188771
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    requires careful control

    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
     зло
    0.51
     стандарт
    0.50
    常规
    0.50
     கல்லற
    0.48
     جرام
    0.47
    城区
    0.46
     bunker
    0.45
    屑
    0.45
     convencional
    0.45
     கல்லறை
    0.44
    POSITIVE LOGITS
     that
    0.47
    {
    0.44
    jení
    0.44
    classAttribute
    0.44
    nur
    0.43
    that
    0.43
    tele
    0.43
     electron
    0.42
     documentaries
    0.42
     CAT
    0.42
    Activations Density 0.001%

    No Known Activations