© 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. 65117
    Prev
    Next
    INDEX
    Explanations

    code snippets and lists

    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
     him
    -0.96
    átek
    -0.86
    щер
    -0.86
     січня
    -0.82
     údaj
    -0.82
     regels
    -0.81
     жовтня
    -0.81
     enfrenta
    -0.79
    crops
    -0.79
    resultMap
    -0.79
    POSITIVE LOGITS
     them
    1.64
    They
    1.21
     they
    1.12
     sorted
    1.10
     They
    1.05
     ihnen
    1.02
     [...
    1.01
     mereka
    1.00
    ([...
    1.00
    他們
    0.99
    Activations Density 0.013%

    No Known Activations