© 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. 190409
    Prev
    Next
    INDEX
    Explanations

    options and choices

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

    words in different languages

    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
            
    0.48
     subspaces
    0.45
     accolades
    0.45
     quests
    0.44
     dawned
    0.44
     snacks
    0.43
    ⚔
    0.43
     subpoenas
    0.42
     lures
    0.41
     dedicated
    0.41
    POSITIVE LOGITS
    Carta
    0.50
     تکلیف
    0.50
     هیڅ
    0.50
    LAGAB
    0.50
    daily
    0.50
    чити
    0.49
     سج
    0.49
     Vors
    0.49
    objClass
    0.49
    窠
    0.48
    Activations Density 0.001%

    No Known Activations