© 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-16K
    7. 10881
    Prev
    Next
    INDEX
    Explanations

    physical stretching and tautness

    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_16k_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
     chim
    0.41
    コート
    0.38
     общения
    0.38
     parks
    0.38
     пар
    0.38
     chimney
    0.38
    嗑
    0.37
     Mif
    0.36
    歿
    0.36
     broadcasting
    0.36
    POSITIVE LOGITS
     stretch
    2.44
     stretching
    2.38
     Stretch
    2.23
    stretch
    2.19
    Stretch
    2.19
     Stretching
    2.17
     stretched
    2.09
     stretches
    2.05
     растя
    2.02
     stretchy
    1.95
    Activations Density 0.224%

    No Known Activations