© 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. 41669
    Prev
    Next
    INDEX
    Explanations

    sets the scene

    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
    -->
    0.50
    AT
    0.48
     ö
    0.48
    ⬝
    0.48
    dy
    0.48
    boosting
    0.47
    ācijas
    0.46
     দায়িত্ব
    0.44
    嫨
    0.44
    0.44
    POSITIVE LOGITS
    ↵↵
    0.56
     Ancient
    0.56
    俨
    0.56
    ق
    0.54
    bibinfo
    0.54
     Winnipeg
    0.53
    кс
    0.52
    ع
    0.52
    )]:
    0.52
     Балтбет
    0.52
    Activations Density 0.000%

    No Known Activations