© 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. 1232
    Prev
    Next
    INDEX
    Explanations

    boring stuff

    np_acts-logits-general · gemini-2.5-flash-lite

    markdown-style structural and formatting cues (bullets, numbering, headings, code/URL tokens, and punctuation that signals lists or sections) indicating instructional or outlined text structure.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
     Elektrokhimiya
    0.21
    ༣
    0.20
     ailments
    0.19
    లం
    0.19
    ัญหา
    0.19
    ausea
    0.19
    音乐
    0.19
    ål
    0.19
     வெப்பநிலை
    0.19
    Bechyné
    0.19
    POSITIVE LOGITS
     dichos
    0.24
     Statement
    0.21
     confluence
    0.20
     and
    0.20
     was
    0.19
     “
    0.19
     faci
    0.19
     వల్ల
    0.18
     namen
    0.18
    所述
    0.18
    Activations Density 2.105%

    No Known Activations