© 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. 40907
    Prev
    Next
    INDEX
    Explanations

    on, up, or importance

    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
    邹
    0.54
    岖
    0.49
    راق
    0.48
     devolución
    0.45
    利亚
    0.44
     vân
    0.44
     프리
    0.43
    誉
    0.43
     ٹی
    0.43
     serii
    0.43
    POSITIVE LOGITS
     եւ
    0.51
    dt
    0.48
    <0xA0>
    0.47
    db
    0.46
     &&
    0.46
    allele
    0.45
    denoted
    0.45
    iphenyl
    0.45
     linearized
    0.44
     &
    0.44
    Activations Density 0.014%

    No Known Activations