© 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. 252977
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    朋友們
    0.54
    ইন্দ
    0.46
    詢
    0.43
    urious
    0.42
    री
    0.42
    மோ
    0.41
     diminish
    0.41
    咱們
    0.40
    akon
    0.40
    شرات
    0.40
    POSITIVE LOGITS
     эш
    0.50
     RETURN
    0.49
     hech
    0.49
    ästä
    0.48
    RETURN
    0.47
     خیال
    0.46
    ే
    0.46
    ROUTE
    0.45
    ECUTIVE
    0.45
    ቸው
    0.44
    Activations Density 0.000%

    No Known Activations