© 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. 125470
    Prev
    Next
    INDEX
    Explanations

    articles with specific follow-ups

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

    analyze data or state

    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
    ific
    0.57
     ประ
    0.55
    बाजी
    0.50
     முழுவதும்
    0.49
     التالية
    0.49
    ahl
    0.49
    icur
    0.48
    𝘱
    0.47
    fect
    0.47
    spur
    0.47
    POSITIVE LOGITS
     preferring
    0.47
     scrubbing
    0.46
     sidelined
    0.46
    selecting
    0.45
     robbers
    0.45
     imitating
    0.44
     cameras
    0.44
     riguardo
    0.44
    一名
    0.43
     Evergreen
    0.43
    Activations Density 0.000%

    No Known Activations