© 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. 68560
    Prev
    Next
    INDEX
    Explanations

    parts and replacement

    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
    isiin
    -1.20
     只
    -1.11
    那我
    -1.08
    啐
    -1.08
     Ideen
    -1.07
     arada
    -1.06
    tillos
    -1.06
    把自己
    -1.05
     detalhe
    -1.05
     cierta
    -1.05
    POSITIVE LOGITS
     or
    1.27
     समस्या
    1.27
     replacement
    1.16
    خيص
    1.16
    焄
    1.12
     but
    1.09
    cuito
    1.09
     causing
    1.04
     sprawd
    1.03
     suffering
    1.00
    Activations Density 0.031%

    No Known Activations