© 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. 114302
    Prev
    Next
    INDEX
    Explanations

    certain phrases and words

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

    natural convection

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.57
     regained
    0.47
    IN
    0.46
     /
    0.45
     refres
    0.43
    ient
    0.43
     suced
    0.43
     .
    0.42
     simplices
    0.42
     reorgan
    0.42
    POSITIVE LOGITS
     エネルギー
    0.56
     القاهرة
    0.54
     निकाले
    0.51
    ⦿
    0.50
     باوجود
    0.49
    AutoStabilise
    0.49
     Ә
    0.49
     پە
    0.49
     проведение
    0.49
     ازيكم
    0.48
    Activations Density 0.000%

    No Known Activations