© 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. 40134
    Prev
    Next
    INDEX
    Explanations

    exponents with numbers

    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
     स्नातक
    0.42
    起源
    0.40
    ỉ
    0.40
    ṇ
    0.40
    ło
    0.39
     ګ
    0.39
     গাছ
    0.38
    lectic
    0.37
     स्कि
    0.37
     witty
    0.37
    POSITIVE LOGITS
    띵
    0.43
    IONES
    0.39
    FDMA
    0.39
     pyruvate
    0.38
    aduras
    0.36
    юза
    0.36
     километров
    0.36
    ਧ
    0.36
    rawdę
    0.35
    DAS
    0.35
    Activations Density 0.001%

    No Known Activations