© 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. 31-GEMMASCOPE-2-RES-262K
    7. 184889
    Prev
    Next
    INDEX
    Explanations

    love and developer

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

    write code

    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_31_width_262k_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
     不需要
    0.49
     sedentary
    0.48
     denser
    0.47
     lump
    0.47
     kitchenette
    0.47
     rise
    0.47
     来
    0.46
     지속
    0.46
     longer
    0.46
     replenished
    0.46
    POSITIVE LOGITS
    a
    0.66
    g
    0.57
    victoria
    0.56
    UN
    0.53
    b
    0.52
    DBG
    0.50
    Psi
    0.49
    edited
    0.49
    FINAL
    0.49
    test
    0.48
    Activations Density 0.000%

    No Known Activations