© 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. 10144
    Prev
    Next
    INDEX
    Explanations

    characters speaking

    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
    suggest
    0.46
    nt
    0.45
    ುದು
    0.44
    utive
    0.44
    ed
    0.43
    assert
    0.42
    他
    0.42
    lls
    0.42
    ocurrencies
    0.42
    confirm
    0.42
    POSITIVE LOGITS
    Faces
    0.43
    ጣል
    0.41
     الوصول
    0.39
     embark
    0.38
     Tach
    0.38
    娄
    0.37
     ليصل
    0.37
    Finding
    0.36
     اپنا
    0.35
     ulaş
    0.35
    Activations Density 0.006%

    No Known Activations