Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 27706
    Prev
    Next
    INDEX
    Explanations

    non-governmental organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    el
    1.37
    is
    1.34
    ни
    1.23
    ade
    1.23
     have
    1.16
    (
    1.13
    é
    1.11
    á
    1.11
    ↵
    1.08
    ur
    1.06
    POSITIVE LOGITS
    டி
    1.08
     increí
    1.07
     intentos
    1.05
     administrativas
    1.04
    י
    1.03
    ।
    1.02
     ﺍ
    0.98
    ア
    0.98
     불구하고
    0.96
     eficiencia
    0.96
    Activations Density 0.001%

    No Known Activations