© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    social networking sites

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

    website paths and topics

    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
     shenanigans
    0.34
     merges
    0.34
     wrappers
    0.33
     fudge
    0.33
     也
    0.32
     hacks
    0.32
     处理
    0.31
     cleanup
    0.31
     monotonic
    0.31
     DOT
    0.31
    POSITIVE LOGITS
    пера
    0.33
    ający
    0.33
    oinette
    0.33
    基督
    0.32
    ançois
    0.31
    olni
    0.31
    ७
    0.31
    ził
    0.31
    ларга
    0.31
    Pastor
    0.30
    Activations Density 0.058%

    No Known Activations