© 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. 31-GEMMASCOPE-2-RES-65K
    7. 11601
    Prev
    Next
    INDEX
    Explanations

    notes and suggestions

    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_31_width_65k_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
    ten
    0.33
     as
    0.32
     a
    0.32
    ▂
    0.32
     an
    0.31
     elucidated
    0.31
    Arm
    0.31
    comes
    0.30
    an
    0.30
     extrapol
    0.29
    POSITIVE LOGITS
     وړیا
    0.37
    ૨
    0.36
     judiciary
    0.35
     właścic
    0.35
     για
    0.35
     regalías
    0.35
     mutlu
    0.35
    izace
    0.35
     privind
    0.34
     щодо
    0.34
    Activations Density 0.078%

    No Known Activations