© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1201
    Prev
    Next
    INDEX
    Explanations

    code punctuation and identifiers

    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
    Negative Logits
    <0xF3>
    0.32
    <0xEC>
    0.29
    т
    0.26
    <0xA9>
    0.25
    ляр
    0.24
    ไ
    0.24
    จ
    0.23
    埃
    0.23
    <0xE8>
    0.23
    IVERSITY
    0.23
    POSITIVE LOGITS
     ताकि
    0.24
     quien
    0.23
     televisi
    0.23
    হাকে
    0.23
     হয়নি
    0.22
     isang
    0.22
     diferentes
    0.22
     copyspace
    0.22
     soli
    0.22
     televisión
    0.21
    Activations Density 0.746%

    No Known Activations