© 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. 49731
    Prev
    Next
    INDEX
    Explanations

    local regions

    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
    vět
    0.45
    ülü
    0.44
    nější
    0.43
    ennen
    0.42
    ündet
    0.41
    ‌ల
    0.40
    amentos
    0.40
     ambigu
    0.40
    间隔
    0.40
    ilem
    0.40
    POSITIVE LOGITS
     influential
    0.46
    品
    0.44
     emotional
    0.41
     regional
    0.41
    շ
    0.40
    プロセス
    0.39
     devout
    0.38
    ヌ
    0.37
     local
    0.37
     regions
    0.37
    Activations Density 0.003%

    No Known Activations