© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119989
    Prev
    Next
    INDEX
    Explanations

    video settings

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

    describing qualities or states

    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
    普
    0.52
     ישראל
    0.50
    vě
    0.50
     פאר
    0.50
     〢
    0.49
     엄청
    0.48
    芬
    0.48
    啊
    0.47
    明星
    0.47
     бу
    0.47
    POSITIVE LOGITS
     HttpException
    0.49
    sman
    0.48
     whiskey
    0.48
     Whiskey
    0.48
     liquor
    0.45
    etown
    0.45
     spiking
    0.44
     Faith
    0.44
    ണ
    0.44
     ResourceManager
    0.43
    Activations Density 0.002%

    No Known Activations