© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127065
    Prev
    Next
    INDEX
    Explanations

    Intel, key, prominent, Holistic, Lab

    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_31_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
    gulpfile
    0.41
    imb
    0.41
     лучших
    0.41
    硗
    0.40
    ли
    0.40
    Лу
    0.40
    让你
    0.40
    zip
    0.40
    𒊭
    0.40
    Teacher
    0.40
    POSITIVE LOGITS
     테스트
    0.43
     fís
    0.40
     fprintf
    0.40
     ACK
    0.40
     arctic
    0.39
     อื่น
    0.39
     muest
    0.39
     IUE
    0.39
    ന്ത
    0.38
     memos
    0.38
    Activations Density 0.006%

    No Known Activations