© 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-65K
    7. 47738
    Prev
    Next
    INDEX
    Explanations

    python main function

    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_65k_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
     ސ
    0.48
    荷兰
    0.44
    Â
    0.44
    quartered
    0.44
     थो
    0.42
    Á
    0.42
     ක
    0.42
    website
    0.42
     quốc
    0.42
    ഓ
    0.42
    POSITIVE LOGITS
    Brewer
    0.43
     hexane
    0.39
     tongs
    0.39
     bist
    0.39
     pores
    0.39
     sulfides
    0.39
     hydrocarbons
    0.39
    ،
    0.39
     pore
    0.38
     abit
    0.38
    Activations Density 0.005%

    No Known Activations