© 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. 22-GEMMASCOPE-RES-131K
    7. 33393
    Prev
    Next
    INDEX
    Explanations

    change and development

    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_22/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
     further
    -1.02
     weiterhin
    -0.92
     attracts
    -0.90
    ddots
    -0.86
     opět
    -0.85
    Addo
    -0.84
     again
    -0.84
     salles
    -0.82
    cydow
    -0.82
     decât
    -0.81
    POSITIVE LOGITS
     transformation
    1.81
     transformations
    1.67
     from
    1.63
     changes
    1.45
    transformation
    1.45
     Transformation
    1.42
     change
    1.41
     Transformations
    1.37
    Transformation
    1.34
     perubahan
    1.27
    Activations Density 0.094%

    No Known Activations