© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    file paths and special characters

    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
     but
    -2.13
     of
    -1.87
    فایل
    -1.65
     so
    -1.64
     is
    -1.63
     now
    -1.60
    𝘞
    -1.52
     after
    -1.50
    ‪.‬‬
    -1.50
     our
    -1.45
    POSITIVE LOGITS
    <h3>
    1.93
    你会
    1.81
            
    1.75
     
    1.67
    健康的
    1.67
    You
    1.64
    你要
    1.64
    ться
    1.59
    即便
    1.58
     Перейти
    1.58
    Activations Density 0.002%

    No Known Activations