© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    index.js file paths

    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
     سپورټ
    0.52
     spooky
    0.50
     amazingly
    0.49
     scary
    0.47
     intimidated
    0.47
     TRANSPORTURI
    0.46
    ב
    0.46
    utivo
    0.44
     বাঙালিদের
    0.44
     sportif
    0.43
    POSITIVE LOGITS
    en
    0.61
    is
    0.59
    em
    0.58
    ig
    0.58
    embra
    0.58
    ol
    0.57
    ang
    0.56
    j
    0.55
    ok
    0.55
    ist
    0.54
    Activations Density 0.001%

    No Known Activations