© 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. 41-GEMMASCOPE-2-RES-262K
    7. 59838
    Prev
    Next
    INDEX
    Explanations

    code style or bpm

    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
    ullar
    0.42
    re
    0.39
     spel
    0.39
    卷
    0.37
    in
    0.37
    υπ
    0.36
    rei
    0.36
    real
    0.36
     l
    0.36
     lull
    0.36
    POSITIVE LOGITS
     popupButton
    0.49
     निर्देशांक
    0.43
     لگائیں
    0.42
    ButtonBar
    0.40
     theseKeys
    0.39
     कुठ
    0.38
     kesin
    0.38
     މަ
    0.38
    กัน
    0.36
    ϟ
    0.36
    Activations Density 0.001%

    No Known Activations