© 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. 80298
    Prev
    Next
    INDEX
    Explanations

    mixed language

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

    raceway, someone, features, built, realization

    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
    ed
    0.57
     dem
    0.51
     stack
    0.51
     /
    0.50
     ruin
    0.49
     signal
    0.48
    -
    0.48
     destiny
    0.48
    cha
    0.48
    E
    0.48
    POSITIVE LOGITS
     टीचिंग
    0.54
    
    0.54
     миро
    0.53
    lié
    0.53
     હું
    0.51
    unächst
    0.51
    ξύ
    0.51
     কোথ
    0.50
    觜
    0.50
     દ્વા
    0.50
    Activations Density 0.000%

    No Known Activations