© 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. 130861
    Prev
    Next
    INDEX
    Explanations

    Martin and Martinez

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

    division and remainders

    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
    開
    0.43
     তাঁকে
    0.42
     createWindow
    0.40
    可能會
    0.40
    开
    0.39
    OpenCamera
    0.38
     kamera
    0.38
    ungkinan
    0.38
     开
    0.37
     সমাধি
    0.37
    POSITIVE LOGITS
     Laur
    0.42
    offel
    0.41
     Nort
    0.41
     Arrest
    0.39
     Laid
    0.39
     Tope
    0.39
     Norwood
    0.39
     Lue
    0.39
     Nauk
    0.38
     Port
    0.38
    Activations Density 0.055%

    No Known Activations