© 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. 229464
    Prev
    Next
    INDEX
    Explanations

    asset to, higher income, location

    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
    )،
    0.53
    ,’
    0.50
    
    0.50
     童
    0.48
    ،
    0.48
    ,&
    0.48
    ⚤
    0.47
    فل
    0.47
    Instructor
    0.47
    isFullscreen
    0.45
    POSITIVE LOGITS
    bewer
    0.47
     చేసిన
    0.46
     keli
    0.46
     યોગ્ય
    0.46
    ikiran
    0.45
     yapt
    0.44
    ंकि
    0.44
     stopping
    0.43
    ban
    0.43
     ਕੀਤਾ
    0.43
    Activations Density 0.001%

    No Known Activations