© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35512
    Prev
    Next
    INDEX
    Explanations

    web request parameters

    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_22/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
     initially
    -0.94
    してました
    -0.93
     personnalisé
    -0.93
     eventually
    -0.92
     tirs
    -0.91
     bronz
    -0.90
     quickly
    -0.86
     intervals
    -0.86
     赤ちゃん
    -0.83
     even
    -0.82
    POSITIVE LOGITS
    が可能
    1.05
     Интернет
    1.02
    angebot
    0.93
    länger
    0.89
     Drama
    0.87
    ServletException
    0.86
     THEM
    0.86
     Эти
    0.85
     WEB
    0.85
     saveurs
    0.85
    Activations Density 0.021%

    No Known Activations