© 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. 84471
    Prev
    Next
    INDEX
    Explanations

    CASE WHEN THEN

    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
     wiederum
    -1.67
     différente
    -1.49
    二日
    -1.44
    してた
    -1.40
    はもう
    -1.39
     immerhin
    -1.38
    ところです
    -1.34
    Недоліки
    -1.34
    してみました
    -1.34
    こちらも
    -1.34
    POSITIVE LOGITS
     Inſ
    1.63
    螃
    1.59
    美丽
    1.48
    ↔
    1.43
     salvajes
    1.43
    guas
    1.42
     they
    1.41
    
    1.39
     the
    1.37
     sadar
    1.37
    Activations Density 0.019%

    No Known Activations