© 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. 57285
    Prev
    Next
    INDEX
    Explanations

    two strings

    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
    قیق
    0.47
    νου
    0.45
    )[[
    0.44
    ی
    0.44
     તેવી
    0.44
    practices
    0.43
     нашим
    0.43
    neux
    0.43
    ﺘ
    0.43
    ئے
    0.43
    POSITIVE LOGITS
     చూడ
    0.49
     הח
    0.48
     TestAvg
    0.48
     מא
    0.45
    mare
    0.44
     Determination
    0.44
     الطل
    0.44
    中华
    0.43
    la
    0.43
     Demand
    0.43
    Activations Density 0.002%

    No Known Activations