© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44546
    Prev
    Next
    INDEX
    Explanations

    feet and pedals

    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
     its
    -1.51
    数据
    -1.30
     others
    -1.21
     other
    -1.16
     véritable
    -1.16
     of
    -1.14
    to
    -1.11
     reconnaître
    -1.10
     berdasarkan
    -1.09
    って感じ
    -1.08
    POSITIVE LOGITS
    ]
    1.21
    esseurs
    1.19
    );
    
    1.16
     известно
    1.14
     {
    
    1.13
    出演
    1.13
    laszt
    1.13
    ['
    1.12
    রা
    1.12
     createSprite
    1.11
    Activations Density 0.035%

    No Known Activations