© 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. 75967
    Prev
    Next
    INDEX
    Explanations

    wing, part, regulation, us, Such

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

    occurrences and directions

    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
     Sebelum
    0.46
     landscapes
    0.45
     sedikit
    0.44
     August
    0.43
     Hackney
    0.42
     A
    0.42
     Socks
    0.42
     from
    0.42
     kilometers
    0.41
     Before
    0.41
    POSITIVE LOGITS
     giỏi
    0.53
     مجموعة
    0.50
     théorème
    0.50
    ಮಾಣ
    0.49
    ithmetic
    0.48
    ição
    0.48
     pangkat
    0.48
    ạn
    0.47
    рия
    0.47
    ޯ
    0.46
    Activations Density 0.003%

    No Known Activations