© 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. 240430
    Prev
    Next
    INDEX
    Explanations

    sets, seats, players, USA

    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
    s
    0.47
     Schwar
    0.47
     Greenhouse
    0.44
     Worker
    0.43
    this
    0.42
    WI
    0.42
     Breakdown
    0.42
    :
    0.42
     d
    0.41
     Liner
    0.41
    POSITIVE LOGITS
     প্যার
    0.55
    жен
    0.54
     Ага
    0.53
    сини
    0.51
     имели
    0.51
     परिचालन
    0.51
     소비
    0.50
     අවශ්‍ය
    0.50
     Бри
    0.50
    спа
    0.50
    Activations Density 0.001%

    No Known Activations