© 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. 3199
    Prev
    Next
    INDEX
    Explanations

    purpose of

    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
     in
    1.10
    ،
    1.02
     be
    1.00
     an
    0.97
     في
    0.95
     a
    0.93
     в
    0.93
    在
    0.90
    ö
    0.80
    曏
    0.80
    POSITIVE LOGITS
    지
    1.20
    ע
    1.15
    ین
    1.02
    anın
    0.94
    ել
    0.93
    ката
    0.93
    ન
    0.91
    ल
    0.88
    ع
    0.88
    ்கள்
    0.88
    Activations Density 0.027%

    No Known Activations