© 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. 193006
    Prev
    Next
    INDEX
    Explanations

    callback context

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

    GTA V Roleplay

    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
    Negative Logits
     colours
    0.52
    ient
    0.47
     [/
    0.46
     Beach
    0.46
     being
    0.45
     beach
    0.45
     notes
    0.45
     Website
    0.45
     Colour
    0.44
    ]
    0.44
    POSITIVE LOGITS
    
    0.50
     તમામ
    0.49
    ٹین
    0.48
    PathTemplate
    0.48
     ქვ
    0.47
     علماء
    0.47
    WithPath
    0.46
     تربیت
    0.46
     پروفیسر
    0.46
     onları
    0.45
    Activations Density 0.001%

    No Known Activations