© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225130
    Prev
    Next
    INDEX
    Explanations

    unveiled its Napoleon Netflix bags

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

    lists, Italian, and Arabic

    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
    ęła
    0.55
    माटर
    0.52
    avacanam
    0.51
    ྞ
    0.51
     फ्लाईओवर
    0.49
     तर
    0.49
     भाजप
    0.49
    েনে
    0.49
    十几
    0.48
     ব্যাটসম্যান
    0.48
    POSITIVE LOGITS
     Saeed
    0.41
    仕様
    0.41
     Fac
    0.40
    zus
    0.40
     Goh
    0.40
     lex
    0.39
    }&\
    0.39
     Mme
    0.39
     Barros
    0.39
     Eber
    0.39
    Activations Density 0.001%

    No Known Activations