© 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. 246317
    Prev
    Next
    INDEX
    Explanations

    cleanup, cleaning, tools

    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
    けど
    0.50
    আছে
    0.48
    )==
    0.47
    ども
    0.47
     রয়েছে
    0.46
     سیس
    0.46
    じ
    0.46
    िकता
    0.46
    衊
    0.46
    鎳
    0.46
    POSITIVE LOGITS
     frü
    0.52
     pelig
    0.49
    ge
    0.49
     slightly
    0.48
    ed
    0.48
    َال
    0.47
    ủ
    0.46
    Spa
    0.45
    slightly
    0.45
    fl
    0.45
    Activations Density 0.001%

    No Known Activations