© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37889
    Prev
    Next
    INDEX
    Explanations

    hiding or seeking shelter

    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_53_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
     ngừa
    0.44
    षी
    0.39
     RSV
    0.38
    bibinfo
    0.38
     chiếu
    0.38
    fontenc
    0.38
     کیشن
    0.37
    ⠊
    0.37
    PageView
    0.37
    ষণ
    0.36
    POSITIVE LOGITS
    躲
    1.48
     hiding
    1.44
     duck
    1.33
     retreated
    1.30
     Duck
    1.23
     hide
    1.20
     retreat
    1.19
    Duck
    1.19
     retreating
    1.19
    duck
    1.18
    Activations Density 0.018%

    No Known Activations