© 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. 242613
    Prev
    Next
    INDEX
    Explanations

    Feedback, other, whatever, made

    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
    ARIO
    0.47
    飞机
    0.46
    눠
    0.45
    钎
    0.44
    dzie
    0.44
    ˵
    0.43
    幼児
    0.43
    实行
    0.43
     নিয়ন্ত্রণ
    0.43
    তবে
    0.42
    POSITIVE LOGITS
     populous
    0.55
    ↵
    0.50
     l
    0.50
     far
    0.48
    pio
    0.48
     possessed
    0.48
     agreg
    0.48
     aggregated
    0.48
    iga
    0.47
    hn
    0.46
    Activations Density 0.002%

    No Known Activations