© 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. 184809
    Prev
    Next
    INDEX
    Explanations

    company illustrations

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

    batter develops

    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
    也許
    0.46
     मुश्किल
    0.44
    ز
    0.43
    房間
    0.42
    誒
    0.42
     relig
    0.41
     dwa
    0.41
     것도
    0.40
     poached
    0.40
    也许
    0.39
    POSITIVE LOGITS
    ätter
    0.49
     Stamps
    0.46
    u
    0.44
                  
    0.43
     çev
    0.43
     webbrowser
    0.41
    atürk
    0.41
    खास्त
    0.40
    큽
    0.40
    ｕ
    0.40
    Activations Density 0.001%

    No Known Activations