© 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. 135029
    Prev
    Next
    INDEX
    Explanations

    stages combined

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

    versions, rectangle, video, glory, artisan, eating, change, Bootstrap

    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
    들도
    0.51
    认定
    0.50
    법
    0.48
    ла
    0.48
     Davies
    0.46
     plupart
    0.45
    ழ
    0.45
     Lyons
    0.45
    मॉन
    0.45
     też
    0.44
    POSITIVE LOGITS
    idh
    0.49
     товар
    0.49
    strstr
    0.48
    DY
    0.48
    دى
    0.46
    *=
    0.46
     *=
    0.45
    mygray
    0.45
    atthakath
    0.44
     воспользоваться
    0.43
    Activations Density 0.001%

    No Known Activations