© 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. 107380
    Prev
    Next
    INDEX
    Explanations

    for liability or errors

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

    musical dance maps country

    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
    лке
    0.51
     inroads
    0.50
    ری
    0.49
    借り
    0.48
    শ
    0.47
    𝚣
    0.47
    ми
    0.47
    쩝
    0.46
    لی
    0.46
    ле
    0.46
    POSITIVE LOGITS
     respons
    0.56
    éta
    0.53
    不僅
    0.50
    él
    0.48
     RIM
    0.48
     eftersom
    0.46
     renom
    0.45
     മാത്രമല്ല
    0.45
     COUNTRY
    0.45
    tra
    0.44
    Activations Density 0.000%

    No Known Activations