© 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. 128917
    Prev
    Next
    INDEX
    Explanations

    let's start a topic

    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
    伥
    -2.13
     dificil
    -1.81
     Penggunaan
    -1.80
    鉿
    -1.78
    놉
    -1.76
     Langkah
    -1.76
     Meningkatkan
    -1.75
    
    -1.72
     preocu
    -1.72
    訁
    -1.71
    POSITIVE LOGITS
    "
    2.31
    an
    1.87
    as
    1.86
    ar
    1.78
    s
    1.77
    al
    1.66
    at
    1.66
    and
    1.63
    u
    1.62
    f
    1.60
    Activations Density 0.009%

    No Known Activations