© 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. 4334
    Prev
    Next
    INDEX
    Explanations

    TAG and logging

    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
     Brecht
    -0.76
     Practice
    -0.72
    europ
    -0.69
    róleo
    -0.67
     PRACTICE
    -0.67
     configuração
    -0.66
     promulgated
    -0.66
     Schweden
    -0.66
     Enzyme
    -0.65
    yente
    -0.65
    POSITIVE LOGITS
     tag
    2.97
     TAG
    2.72
    TAG
    2.67
     Tag
    2.56
    tag
    2.50
     tags
    2.48
    Tag
    2.47
    getTag
    2.33
     Tags
    2.11
     tagging
    2.09
    Activations Density 0.022%

    No Known Activations