© 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. 39609
    Prev
    Next
    INDEX
    Explanations

    numbers separated by characters

    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
    
    -1.34
     in
    -1.16
    ffiche
    -1.16
     tableta
    -1.16
    './
    -1.13
    #"
    -1.12
     jLabel
    -1.12
     jTextField
    -1.09
    СТА
    -1.08
    ˂
    -1.08
    POSITIVE LOGITS
    0
    1.19
     gebaut
    1.13
    _
    1.13
    9
    1.11
    越是
    1.03
    8
    1.03
     numerous
    1.02
     muhte
    1.00
     einiges
    1.00
     nachher
    0.98
    Activations Density 0.017%

    No Known Activations