© 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. 21495
    Prev
    Next
    INDEX
    Explanations

    screws and bolts

    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
     rigid
    0.49
     isotherms
    0.48
     ríg
    0.43
    rigid
    0.42
     échanc
    0.41
    attached
    0.40
     membranes
    0.39
    砣
    0.39
     rigidity
    0.39
     integrada
    0.39
    POSITIVE LOGITS
     screws
    1.55
     screw
    1.45
     Screw
    1.34
    Screw
    1.27
    螺
    1.27
    screw
    1.21
     screwed
    1.19
     Schra
    1.16
     screwing
    1.13
     fasteners
    1.09
    Activations Density 0.008%

    No Known Activations