© 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. 14253
    Prev
    Next
    INDEX
    Explanations

    html tag starts

    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
     our
    -2.17
     suavemente
    -1.92
     preparar
    -1.84
    aporan
    -1.83
     this
    -1.82
    %).
    -1.81
     rodeado
    -1.80
    地区的
    -1.77
     کردیم
    -1.75
     ujedno
    -1.73
    POSITIVE LOGITS
    ;.
    2.05
     VERY
    2.03
    ࿊
    2.02
    婞
    1.95
    vereignty
    1.92
    ᯾
    1.91
    ledad
    1.88
    
    1.86
    Ⲉ
    1.86
    几个人
    1.86
    Activations Density 0.036%

    No Known Activations