© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38926
    Prev
    Next
    INDEX
    Explanations

    rehearsal and rehearing denied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &#
    -2.59
     crée
    -2.39
     terrifying
    -2.19
    ığında
    -2.19
     ſever
    -2.16
     disgusting
    -2.11
     preſ
    -2.09
    轵
    -2.09
     линия
    -2.02
    犼
    -2.02
    POSITIVE LOGITS
    🕺
    2.39
    🤭
    2.13
    鹉
    2.09
     главным
    2.08
    珝
    2.06
    媖
    2.06
    😫
    2.05
     lanka
    2.03
     libremente
    2.02
     土産
    1.98
    Activations Density 0.006%

    No Known Activations