© 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. 12918
    Prev
    Next
    INDEX
    Explanations

    resource

    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
     óculos
    -2.33
    秾
    -2.19
     lamented
    -2.17
    翃
    -2.11
     cabelo
    -2.06
     interwoven
    -2.03
    訐
    -2.03
    由於
    -2.03
    ꜆
    -2.03
    altra
    -2.00
    POSITIVE LOGITS
     is
    3.00
     \
    2.70
     
    2.63
     portugués
    2.52
     alemán
    2.45
    bodyParser
    2.34
    鈇
    2.33
    笋
    2.31
     francés
    2.27
    ⢓
    2.27
    Activations Density 0.015%

    No Known Activations