© 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. 258805
    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
     hưởng
    0.45
     звук
    0.42
     вмеша
    0.41
    ₚ
    0.40
     κάπο
    0.40
     коопера
    0.39
     মর্যাদা
    0.39
     рома
    0.39
    辣
    0.38
    掴
    0.38
    POSITIVE LOGITS
    POSED
    0.51
    يس
    0.47
    QUES
    0.47
    ில்
    0.46
    il
    0.46
     chh
    0.46
    Figures
    0.45
     loadImage
    0.45
     artery
    0.45
    ü
    0.45
    Activations Density 0.001%

    No Known Activations