© 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. 50126
    Prev
    Next
    INDEX
    Explanations

    code parameterization

    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
     marginBottom
    -0.77
    .............
    -0.73
    Binder
    -0.69
     tử
    -0.69
    Resultado
    -0.68
    icha
    -0.68
     Universidades
    -0.66
    nextProps
    -0.65
    weebly
    -0.65
    uuid
    -0.65
    POSITIVE LOGITS
     Vì
    0.76
    સ્
    0.72
    arParams
    0.72
    Paging
    0.70
    Abitanti
    0.69
    czy
    0.69
    次数
    0.68
     Enabling
    0.67
    Ц
    0.66
     зна
    0.65
    Activations Density 0.606%

    No Known Activations