© 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. 71298
    Prev
    Next
    INDEX
    Explanations

    usefullikemosthelpfulproblemif

    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
     currently
    -1.92
     now
    -1.66
     being
    -1.44
     diren
    -1.38
     perna
    -1.37
     buna
    -1.35
    currently
    -1.34
     kini
    -1.30
    マジで
    -1.29
    ícias
    -1.28
    POSITIVE LOGITS
     able
    1.44
     if
    1.39
     be
    1.33
    rhos
    1.27
     galima
    1.20
     samym
    1.17
    charles
    1.17
    aiuto
    1.13
    usure
    1.12
     algunos
    1.09
    Activations Density 0.091%

    No Known Activations