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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 87380
    Prev
    Next
    INDEX
    Explanations

    mac and cheese recipes

    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
     exactamente
    0.57
     CCSDT
    0.57
     يا
    0.56
    鈈
    0.56
     сим
    0.56
     ವರ್ಷ
    0.56
     HDI
    0.55
    ಳೆದ
    0.55
     конкурен
    0.54
    \!
    0.54
    POSITIVE LOGITS
    omes
    0.55
    Int
    0.54
     I
    0.54
    ch
    0.54
    esse
    0.54
    add
    0.53
    ka
    0.52
    ENG
    0.52
    V
    0.52
    기
    0.52
    Activations Density 0.000%

    No Known Activations