© 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. 100681
    Prev
    Next
    INDEX
    Explanations

    each other

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

    body {

    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
     vertical
    0.46
    或
    0.46
    และ
    0.46
    หรือ
    0.46
     ,
    0.46
     hb
    0.44
     would
    0.43
    ("
    0.42
     inte
    0.42
     auto
    0.42
    POSITIVE LOGITS
     Каждый
    0.53
     Jeder
    0.52
    吃飯
    0.52
    紓
    0.51
     Każ
    0.50
     Chaque
    0.50
    laughs
    0.48
     उत्सव
    0.48
     দার্শনিক
    0.48
    巿
    0.47
    Activations Density 0.000%

    No Known Activations