© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192416
    Prev
    Next
    INDEX
    Explanations

    production base

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

    Homemade Lava

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    의
    0.52
     Pel
    0.46
     Guzman
    0.46
    <td>
    0.46
    로
    0.44
     Mas
    0.43
     of
    0.42
     do
    0.41
     Canyon
    0.41
    ke
    0.41
    POSITIVE LOGITS
     сериа
    0.53
    rifugal
    0.52
     operat
    0.52
    yatiti
    0.52
    𢎞
    0.50
    绩
    0.49
     traité
    0.49
     montée
    0.49
     proj
    0.48
    interacting
    0.48
    Activations Density 0.006%

    No Known Activations