© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137305
    Prev
    Next
    INDEX
    Explanations

    backbone and spine

    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_40_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
     offices
    0.46
     bathrooms
    0.43
     office
    0.43
     point
    0.43
     null
    0.42
     deduct
    0.42
     ü
    0.40
     science
    0.40
     balls
    0.39
     milit
    0.39
    POSITIVE LOGITS
     backbone
    1.73
     spine
    1.63
     Backbone
    1.41
     Spine
    1.37
    spine
    1.33
     spines
    1.31
     SPINE
    1.21
     spinal
    1.02
    脊
    0.97
     Spinal
    0.91
    Activations Density 0.027%

    No Known Activations