© 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. 88068
    Prev
    Next
    INDEX
    Explanations

    AMP pages

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

    analog clocks and layers

    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
     那麼
    0.55
    他們
    0.54
    所以在
    0.48
    avis
    0.48
    ಟ
    0.48
    aken
    0.47
    ixon
    0.46
    وتي
    0.46
    所以
    0.46
    ix
    0.45
    POSITIVE LOGITS
     Dunes
    0.45
     pelang
    0.42
     wrześ
    0.41
    ிலுள்ள
    0.41
     KJ
    0.40
     chimique
    0.39
     generation
    0.39
     IPv
    0.39
    锁
    0.39
    জী
    0.39
    Activations Density 0.001%

    No Known Activations