© 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-16K
    7. 13019
    Prev
    Next
    INDEX
    Explanations

    well, no, pain

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

    causes and relations

    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_16k_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
    द्योगिकी
    0.48
    س
    0.44
     ถึง
    0.44
     склад
    0.42
     SECTION
    0.42
    หัส
    0.42
     фу
    0.41
    від
    0.41
     cutout
    0.41
     ו
    0.41
    POSITIVE LOGITS
    اا
    0.44
    తర
    0.44
    RelativeTo
    0.43
    ৃত
    0.43
    aar
    0.42
    的状态
    0.42
    endaten
    0.41
    eb
    0.41
     Veteran
    0.41
     Panda
    0.40
    Activations Density 0.002%

    No Known Activations