© 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-65K
    7. 148
    Prev
    Next
    INDEX
    Explanations

    contractions of not

    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_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
     and
    0.66
    UserData
    0.57
    د
    0.54
     மற்றும்
    0.54
    ری
    0.51
    Z
    0.51
    IS
    0.51
    Man
    0.51
    および
    0.50
    인
    0.50
    POSITIVE LOGITS
    0.61
     muttered
    0.50
    o
    0.48
     boiled
    0.45
     struggled
    0.45
    ru
    0.45
     মতে
    0.45
     scolded
    0.44
     sickly
    0.44
     ƒ
    0.44
    Activations Density 0.296%

    No Known Activations