© 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. 115766
    Prev
    Next
    INDEX
    Explanations

    `.dll` or `PATH` or `Include`

    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
     PropTypes
    -0.76
    eze
    -0.76
     व्यक्ति
    -0.74
    掛
    -0.73
     grasp
    -0.72
    Ꮩ
    -0.70
    mány
    -0.69
    REDIRECT
    -0.68
    лая
    -0.68
     sü
    -0.68
    POSITIVE LOGITS
     italic
    0.81
    Kelvin
    0.71
    電視
    0.70
    マジック
    0.70
     desi
    0.69
     spd
    0.69
     acquis
    0.68
    rison
    0.67
     diter
    0.66
     liquors
    0.66
    Activations Density 0.023%

    No Known Activations