© 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. 247392
    Prev
    Next
    INDEX
    Explanations

    directory or folder

    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
    문에
    0.49
    覚
    0.47
    不懂
    0.45
    민
    0.45
    남
    0.44
    聽到
    0.44
    謊
    0.43
     못한
    0.43
    護
    0.43
    ችል
    0.43
    POSITIVE LOGITS
     Simplify
    0.49
    infect
    0.46
    dag
    0.44
    ép
    0.44
     fungicides
    0.43
    Simplify
    0.43
     регуляр
    0.42
    olines
    0.42
     fungicide
    0.41
    सायनिक
    0.41
    Activations Density 0.001%

    No Known Activations