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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 17603
    Prev
    Next
    INDEX
    Explanations

    nut or nuts

    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
    م
    1.35
    ку
    1.26
    ம்
    1.24
    ни
    1.23
    м
    1.12
    ม
    1.10
    지와
    1.08
    ج
    1.08
    ки
    1.05
     técnicos
    1.04
    POSITIVE LOGITS
     as
    1.47
     nut
    1.23
     at
    1.16
     for
    1.15
     on
    1.10
     are
    1.10
     nuts
    1.10
    ’
    1.09
    ra
    1.08
    י
    1.07
    Activations Density 0.004%

    No Known Activations