© 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. 72691
    Prev
    Next
    INDEX
    Explanations

    funeral arrangements, profiles list, hunter rank

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

    multiBTC pairs

    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
    venidos
    0.50
    ⊷
    0.49
    Million
    0.48
     свето
    0.47
     الثانوي
    0.47
    dihydroxy
    0.45
    $-$,
    0.44
    役割
    0.44
    カイブ
    0.44
    િલે
    0.43
    POSITIVE LOGITS
     Anh
    0.49
    ari
    0.45
     imme
    0.44
     Meri
    0.43
     genoemd
    0.42
     Lind
    0.42
    ü
    0.42
     pal
    0.41
     iaa
    0.40
    ç
    0.40
    Activations Density 0.000%

    No Known Activations