© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59033
    Prev
    Next
    INDEX
    Explanations

    primary patent numbers

    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
    istungs
    -0.85
    AnchorStyles
    -0.77
    ㅎ
    -0.77
    вушка
    -0.77
    слу
    -0.75
    formatie
    -0.74
    íamos
    -0.74
    develop
    -0.74
    ントランス
    -0.74
    ︰
    -0.73
    POSITIVE LOGITS
    Primary
    1.09
     Primary
    1.08
     primary
    1.05
    primary
    0.99
    このように
    0.81
    衒
    0.74
    listo
    0.73
     Jams
    0.73
    ản
    0.73
     stressed
    0.73
    Activations Density 0.020%

    No Known Activations