© 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. 71853
    Prev
    Next
    INDEX
    Explanations

    defective parents Code partner password

    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
     by
    -2.70
     in
    -2.19
     at
    -2.03
     on
    -1.70
     that
    -1.70
     When
    -1.66
     Because
    -1.62
     If
    -1.61
     every
    -1.60
     which
    -1.57
    POSITIVE LOGITS
    畋
    1.77
    ఝ
    1.70
     adesi
    1.61
     kinda
    1.59
    anmoins
    1.55
    
    1.52
    ೞ
    1.52
     Tercera
    1.52
     撮っ
    1.52
     イラストレーション
    1.50
    Activations Density 0.205%

    No Known Activations