© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 36212
    Prev
    Next
    INDEX
    Explanations

    python setup

    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
     어려
    0.41
    щения
    0.37
    
    0.37
     subnet
    0.37
    泉
    0.37
    ufer
    0.36
     うる
    0.36
    氖
    0.36
    Ბ
    0.35
     inward
    0.35
    POSITIVE LOGITS
     setup
    2.81
    setup
    2.70
     Setup
    2.63
    Setup
    2.56
     setups
    2.44
     SETUP
    2.28
    SETUP
    2.17
     सेटअप
    2.08
    SetUp
    1.74
    setUp
    1.66
    Activations Density 0.020%

    No Known Activations