© 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. 8687
    Prev
    Next
    INDEX
    Explanations

    media in tech contexts

    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
    E
    -2.78
     —
    -2.66
     es
    -2.44
     cũng
    -2.42
     similarly
    -2.42
     می‌توان
    -2.36
    ();
    -2.36
    I
    -2.34
     Also
    -2.33
    also
    -2.31
    POSITIVE LOGITS
    
    3.03
    狆
    2.73
    渽
    2.66
    菝
    2.63
    嗞
    2.58
    趼
    2.52
    𖥦
    2.50
    Bahan
    2.47
    Ukuran
    2.44
    ỽ
    2.44
    Activations Density 0.020%

    No Known Activations