© 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. 156798
    Prev
    Next
    INDEX
    Explanations

    evaluating control or ordering

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

    most conservative original

    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
    ཎ
    0.55
    subNav
    0.52
    Ყ
    0.50
     regularmente
    0.50
     nonradiative
    0.47
     multiplic
    0.46
     გვ
    0.46
     oldCount
    0.46
    ിയും
    0.45
    ༦
    0.45
    POSITIVE LOGITS
     unjust
    0.47
    iszt
    0.46
     Through
    0.45
     mistaken
    0.45
     Paper
    0.45
    weiss
    0.43
    無理
    0.43
    !(
    0.43
    !,
    0.43
     Sandy
    0.43
    Activations Density 0.000%

    No Known Activations