© 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. 157640
    Prev
    Next
    INDEX
    Explanations

    services, public, cases, scientists, plan

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

    important, increasing, adding

    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
    سازی
    0.51
     deco
    0.48
     教え
    0.47
     illumin
    0.47
     disturbs
    0.47
     여섯
    0.46
     load
    0.45
    缫
    0.45
     illumination
    0.45
     ทำให้
    0.45
    POSITIVE LOGITS
    Imperial
    0.47
    中華
    0.47
    UM
    0.45
    OUR
    0.45
     N
    0.44
    EE
    0.44
     выполнять
    0.44
    ா
    0.43
    ంప
    0.43
    인
    0.43
    Activations Density 0.000%

    No Known Activations