© 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. 102473
    Prev
    Next
    INDEX
    Explanations

    singing songs and hymns

    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
    -3.17
     let
    -2.58
     leur
    -2.34
                 
    -2.31
    titial
    -2.28
    轳
    -2.27
    ="")
    -2.25
     is
    -2.25
     neutron
    -2.23
     tenho
    -2.22
    POSITIVE LOGITS
    C
    3.16
    
    2.75
    o
    2.75
     遊戲
    2.73
     迷你
    2.47
    B
    2.47
    D
    2.39
     zelve
    2.30
     فنا
    2.22
     イベント
    2.20
    Activations Density 0.004%

    No Known Activations