© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42160
    Prev
    Next
    INDEX
    Explanations

    instructions or descriptionsactions and their purposeconditional actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нди
    0.45
    личие
    0.44
    శి
    0.44
    стал
    0.43
    ស្ថានភាព
    0.43
    义
    0.42
    చ
    0.42
    ன்று
    0.41
     livros
    0.41
    ಭವ
    0.41
    POSITIVE LOGITS
     बीजेपी
    0.40
     ഗു
    0.40
     tombe
    0.40
     करणाऱ्या
    0.40
     muque
    0.39
     )
    0.39
     Bol
    0.39
     साझे
    0.39
    정이
    0.39
     Rab
    0.39
    Activations Density 0.001%

    No Known Activations