© 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. 40-GEMMASCOPE-2-RES-262K
    7. 26124
    Prev
    Next
    INDEX
    Explanations

    margin:

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     |”
    0.42
    රා
    0.42
    让我们
    0.41
    Biographie
    0.41
    PlayerDataCache
    0.41
    ျေး
    0.40
    Apache
    0.40
     peacefully
    0.40
    Lyrics
    0.40
     በጥ
    0.39
    POSITIVE LOGITS
    <b>
    0.80
    </i>
    0.47
     content
    0.42
    issimi
    0.41
    0.40
    <i>
    0.40
     invest
    0.39
     modular
    0.38
     continua
    0.38
    <strong>
    0.37
    Activations Density 0.001%

    No Known Activations