© 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. 94095
    Prev
    Next
    INDEX
    Explanations

    template filenames and types

    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
     prakti
    -0.76
     MÉXICO
    -0.72
     Rehab
    -0.72
     THEORY
    -0.69
     moniker
    -0.68
    леный
    -0.67
     hagas
    -0.67
    xuan
    -0.67
    Wallis
    -0.65
    MinMax
    -0.64
    POSITIVE LOGITS
     template
    5.34
     templates
    4.78
    template
    4.25
     Template
    3.67
    模板
    3.63
    Template
    3.58
    templates
    3.48
     Templates
    3.41
    TEMPLATE
    3.31
     шабло
    3.09
    Activations Density 0.085%

    No Known Activations