© 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. 45161
    Prev
    Next
    INDEX
    Explanations

    closing brackets and delimiters

    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
    และ
    -1.93
     hanya
    -1.81
    ꜆
    -1.75
     și
    -1.71
     親
    -1.64
    翃
    -1.63
     riport
    -1.63
    刄
    -1.58
     riscos
    -1.54
    事も
    -1.53
    POSITIVE LOGITS
    </b>
    1.59
    りますが
    1.51
     Grundstück
    1.47
    ,
    1.45
    3
    1.44
    鉝
    1.42
    
    1.40
    鉺
    1.39
    pregunt
    1.35
     Wohnzimmer
    1.35
    Activations Density 0.103%

    No Known Activations