© 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. 231630
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
     identifies
    0.51
    uny
    0.50
    >′</
    0.48
     R
    0.47
     describes
    0.46
     tratar
    0.45
    árt
    0.44
     mediates
    0.44
     Biz
    0.43
     Vul
    0.43
    POSITIVE LOGITS
    ใน
    0.56
    開始
    0.56
    ঔ
    0.51
    نم
    0.50
     بچوں
    0.50
    漸
    0.50
    되
    0.49
    動
    0.48
     بچے
    0.47
    畳
    0.47
    Activations Density 0.000%

    No Known Activations