© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 53963
    Prev
    Next
    INDEX
    Explanations

    names of people, places, and things

    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
     tigre
    -1.69
     eléct
    -1.63
     oogen
    -1.63
     kesel
    -1.62
    𓆏
    -1.59
     boute
    -1.59
     mauva
    -1.58
     desnuda
    -1.55
     indiví
    -1.54
     westfalen
    -1.53
    POSITIVE LOGITS
     That
    1.59
    no
    1.57
     So
    1.48
     It
    1.43
     By
    1.42
    y
    1.41
    It
    1.41
     And
    1.41
     From
    1.41
     As
    1.37
    Activations Density 0.446%

    No Known Activations