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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2462
    Prev
    Next
    INDEX
    Explanations

    purpose or use

    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_40_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
     breaks
    0.44
     celebrated
    0.43
     sellest
    0.41
    ემის
    0.40
     dilaksanakan
    0.40
     afin
    0.39
    డంలో
    0.39
    詬
    0.39
     sake
    0.38
    dalam
    0.38
    POSITIVE LOGITS
     для
    2.38
     für
    2.19
     για
    2.13
     for
    2.06
     برای
    2.06
    สำหรับ
    2.02
     untuk
    2.00
     pentru
    1.97
    для
    1.88
    สำหรับการ
    1.88
    Activations Density 0.296%

    No Known Activations