© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1244
    Prev
    Next
    INDEX
    Explanations

    objects, value, and movement

    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
     Yuen
    -0.79
     urn
    -0.75
    TypeMap
    -0.74
    成为
    -0.74
    ሃ
    -0.72
    tolerance
    -0.71
    श्चित
    -0.69
     parceria
    -0.69
     sämtliche
    -0.69
     becoming
    -0.68
    POSITIVE LOGITS
     item
    1.17
     objects
    1.10
     object
    1.05
     arg
    1.00
     obj
    0.98
    obj
    0.94
     объекта
    0.92
     value
    0.91
     objectAtIndex
    0.88
     объект
    0.88
    Activations Density 0.015%

    No Known Activations