© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1880
    Prev
    Next
    INDEX
    Explanations

    muscle at diaphragm

    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
     origen
    0.49
    í
    0.49
    å
    0.47
     acaso
    0.46
     zaidi
    0.46
    iving
    0.45
    ā
    0.45
    ack
    0.44
    c
    0.44
    ෙකු
    0.44
    POSITIVE LOGITS
     עם
    0.51
     با
    0.46
     verlassen
    0.46
     הש
    0.43
     ప్ర
    0.43
     פר
    0.43
    Propagation
    0.42
     공
    0.42
    空白
    0.42
    捲
    0.42
    Activations Density 0.001%

    No Known Activations