© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26762
    Prev
    Next
    INDEX
    Explanations

    chew bones and fetch

    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
    Negative Logits
    ्यूशन
    0.42
     domesticated
    0.41
    Glas
    0.39
     Breeding
    0.39
    ພັນ
    0.39
     breeding
    0.38
     Shining
    0.38
    锦
    0.37
     Murcia
    0.37
     Illness
    0.36
    POSITIVE LOGITS
     chew
    1.02
     bone
    0.98
    骨
    0.91
     bones
    0.88
    Bone
    0.88
     Bone
    0.86
     chewed
    0.84
     chewing
    0.83
     chewy
    0.78
     Bones
    0.77
    Activations Density 0.004%

    No Known Activations