© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64280
    Prev
    Next
    INDEX
    Explanations

    import or site setup

    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
    ffic
    -0.91
     plantar
    -0.85
    riac
    -0.73
    飲
    -0.73
     admin
    -0.73
    mce
    -0.71
     nothingness
    -0.70
     piezo
    -0.69
     intu
    -0.68
    𝑹
    -0.68
    POSITIVE LOGITS
     import
    0.95
     importar
    0.94
     imports
    0.94
     imported
    0.92
     Import
    0.92
     importation
    0.91
     sites
    0.85
    sites
    0.85
    import
    0.84
     importe
    0.81
    Activations Density 0.019%

    No Known Activations