© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9376
    Prev
    Next
    INDEX
    Explanations

    jeans and leg sections

    np_acts-logits-general · gemini-2.5-flash-lite

    clothing and body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    肩
    0.73
     Neck
    0.68
     shoulder
    0.66
     Shoulder
    0.66
    Neck
    0.64
     shoulders
    0.62
     neck
    0.61
     necks
    0.61
    shoulder
    0.60
    肩膀
    0.59
    POSITIVE LOGITS
    腿
    1.81
     leg
    1.59
     legs
    1.56
     thigh
    1.55
     Leg
    1.51
     Legs
    1.46
     thighs
    1.41
    褲
    1.41
    Leg
    1.40
    裤
    1.40
    Activations Density 0.273%

    No Known Activations