© 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-262K
    7. 24509
    Prev
    Next
    INDEX
    Explanations

    copy and paste

    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
     ulterior
    0.48
     assassin
    0.48
    ور
    0.47
    <unused2140>
    0.46
     buscas
    0.46
     کوم
    0.45
     moistur
    0.44
    ंगर
    0.44
    ூ
    0.44
     alternates
    0.43
    POSITIVE LOGITS
    Copy
    1.37
     copy
    1.34
     Copy
    1.31
    copy
    1.28
    复制
    1.27
     copying
    1.27
    拷贝
    1.20
     копи
    1.20
     copies
    1.19
    複製
    1.13
    Activations Density 0.064%

    No Known Activations