© 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. 12738
    Prev
    Next
    INDEX
    Explanations

    to you or your

    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
     l
    -1.28
    ag
    -1.23
    ant
    -1.20
    be
    -1.09
    h
    -1.06
    u
    -1.06
     p
    -1.05
    le
    -1.04
    l
    -1.04
    ak
    -1.02
    POSITIVE LOGITS
     októ
    1.46
     remarqu
    1.45
     your
    1.45
     stratég
    1.31
     Hacer
    1.30
     dátum
    1.27
     Início
    1.27
     bolsillos
    1.26
     komfort
    1.26
     kto
    1.26
    Activations Density 0.021%

    No Known Activations