© 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. 246846
    Prev
    Next
    INDEX
    Explanations

    comments and feedback regarding

    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
    媇
    0.54
    鲐
    0.47
     \}$
    0.46
    粎
    0.46
     यांनी
    0.45
    öd
    0.44
    endon
    0.44
    ocken
    0.44
    䀠
    0.44
     यांना
    0.43
    POSITIVE LOGITS
     Commune
    0.56
     Кор
    0.54
     subversive
    0.53
     Cora
    0.53
     piscine
    0.50
     Howe
    0.49
     campanha
    0.48
     Kor
    0.47
     campagne
    0.47
    JPG
    0.47
    Activations Density 0.000%

    No Known Activations