© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7101
    Prev
    Next
    INDEX
    Explanations

    doing things I can

    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_262k_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
    这是一个
    0.25
    这
    0.23
    没有任何
    0.23
    this
    0.23
    there
    0.23
    2
    0.22
    它
    0.22
     reversing
    0.22
     something
    0.21
    ၂
    0.21
    POSITIVE LOGITS
     gebruiken
    0.24
    積極的に
    0.22
     inev
    0.21
    gger
    0.21
     ประกอบ
    0.21
     적극
    0.20
     cotidian
    0.20
    руют
    0.19
    瑯
    0.19
     активно
    0.19
    Activations Density 0.527%

    No Known Activations