© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119109
    Prev
    Next
    INDEX
    Explanations

    Hire top performers

    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_34/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
    кия
    -0.90
     kommentar
    -0.86
    </h2>
    -0.82
     アニメ
    -0.81
    してほしい
    -0.80
    Provincia
    -0.75
     nivå
    -0.75
    ЩИ
    -0.75
     костюм
    -0.75
     fortæller
    -0.75
    POSITIVE LOGITS
    seemed
    0.92
     erne
    0.87
    setDefault
    0.82
    ú
    0.80
    ु
    0.78
     aquella
    0.78
    нансо
    0.77
     starting
    0.77
     REMOV
    0.76
     Waterfront
    0.76
    Activations Density 0.000%

    No Known Activations