© 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-65K
    7. 51013
    Prev
    Next
    INDEX
    Explanations

    leg, leggings, legality

    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_65k_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
    t
    0.48
    il
    0.46
    ık
    0.43
     공동
    0.43
    ctive
    0.42
    ý
    0.42
    די
    0.41
    共同
    0.39
    ik
    0.38
    肱
    0.38
    POSITIVE LOGITS
     Leg
    0.88
    Leg
    0.82
     leg
    0.80
     lég
    0.72
     LEG
    0.71
    leg
    0.69
    LEG
    0.66
     legumes
    0.65
     legis
    0.64
     leggings
    0.63
    Activations Density 0.023%

    No Known Activations