© 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. 9310
    Prev
    Next
    INDEX
    Explanations

    Chandelier

    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
     onerous
    0.36
     nomencl
    0.33
     setState
    0.32
    กรณี
    0.32
     rédaction
    0.32
     ආකාර
    0.32
     incriminating
    0.31
    သည့်
    0.30
     organismes
    0.30
    ⵏ
    0.30
    POSITIVE LOGITS
     Wood
    0.35
     Gu
    0.35
     Excellent
    0.34
     Stone
    0.34
     Honey
    0.34
     looks
    0.33
     Fire
    0.33
     niewiel
    0.33
     Hu
    0.33
     Lu
    0.32
    Activations Density 0.024%

    No Known Activations