© 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. 22-GEMMASCOPE-RES-131K
    7. 69003
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes and values

    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
     剑
    -1.09
     offrir
    -1.08
     太阳
    -1.06
    tata
    -1.05
    Flickr
    -1.04
     restes
    -1.02
     chaus
    -1.02
    chica
    -0.99
    HAHA
    -0.99
     distinguer
    -0.98
    POSITIVE LOGITS
     vital
    1.00
     became
    0.94
     burgeoning
    0.92
    TextFormField
    0.90
     or
    0.90
     required
    0.90
     profoundly
    0.90
     lead
    0.89
     now
    0.89
     purposefully
    0.88
    Activations Density 0.001%

    No Known Activations