© 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. 6513
    Prev
    Next
    INDEX
    Explanations

    desired states and requirements

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

    mixed language punctuation

    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
    𝘬
    0.43
    イナー
    0.42
     möglichen
    0.41
    pecific
    0.40
     spezif
    0.39
     (%)
    0.38
    部の
    0.37
    類の
    0.37
    側の
    0.37
    機の
    0.36
    POSITIVE LOGITS
    。『
    0.50
    だけでなく
    0.46
    的同时
    0.43
    .&
    0.43
    同时也
    0.42
    はもちろん
    0.41
    และ
    0.41
    ｡
    0.41
    ‌.
    0.40
    
    0.40
    Activations Density 0.445%

    No Known Activations