© 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. 239126
    Prev
    Next
    INDEX
    Explanations

    turn table or turn

    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
    ποί
    0.48
    ගෙන
    0.47
    izacja
    0.46
     १४
    0.44
    িশীল
    0.44
     눌
    0.43
    izarea
    0.43
     परस्मैपदी
    0.42
    ую
    0.42
    ेलो
    0.41
    POSITIVE LOGITS
    curs
    0.55
    cus
    0.47
    Ford
    0.47
    紅
    0.47
    red
    0.45
    Emma
    0.45
    Didn
    0.45
    貨
    0.45
     উদ্ধ
    0.44
    Johnny
    0.44
    Activations Density 0.000%

    No Known Activations