© 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. 93954
    Prev
    Next
    INDEX
    Explanations

    tags and versions

    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
    VENUE
    -0.78
     fau
    -0.75
    佥
    -0.73
    Epidemiology
    -0.71
    াপ
    -0.70
    啉
    -0.70
     devin
    -0.70
    HANGUL
    -0.69
    APON
    -0.69
     اپ
    -0.67
    POSITIVE LOGITS
     tag
    3.28
    tag
    3.00
    Tag
    2.80
     Tag
    2.75
     tags
    2.48
     tagging
    2.42
    TAG
    2.34
     tagged
    2.34
     TAG
    2.27
    getTag
    2.20
    Activations Density 0.092%

    No Known Activations