© 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. 41-GEMMASCOPE-2-RES-262K
    7. 102776
    Prev
    Next
    INDEX
    Explanations

    bug, worm, insect

    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_all/layer_41_width_262k_l0_big
    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
     escalated
    0.44
    ާ
    0.43
     hızlı
    0.42
     быстро
    0.41
     Issues
    0.40
     Incident
    0.40
    frast
    0.39
     escalate
    0.38
     complain
    0.38
    快速
    0.38
    POSITIVE LOGITS
     bugs
    1.48
     worms
    1.30
     insects
    1.26
    虫
    1.24
    bugs
    1.23
     bug
    1.21
     insect
    1.20
     Bugs
    1.20
    蟲
    1.13
     worm
    1.13
    Activations Density 0.001%

    No Known Activations