© 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. 60147
    Prev
    Next
    INDEX
    Explanations

    descriptions or lists

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

    flavor explosion

    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
    akumar
    0.44
     핵심
    0.43
     நட்சத்திர
    0.41
    ổ
    0.41
    ↵
    0.41
     ایر
    0.41
    kob
    0.41
     cỏ
    0.41
     стару
    0.40
    ė
    0.40
    POSITIVE LOGITS
    敵人
    0.51
    社區
    0.51
     Malaria
    0.50
    收聽
    0.48
     Containers
    0.46
     Конгрегация
    0.46
     Masjid
    0.46
    㣩
    0.46
    娛
    0.46
     soziale
    0.46
    Activations Density 0.000%

    No Known Activations