© 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. 54079
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     baratas
    -1.17
     especiais
    -1.17
    おわりに
    -1.13
    więcej
    -1.11
    rzost
    -1.11
    lihatan
    -1.11
     celulares
    -1.06
    więks
    -1.06
     bicicleta
    -1.03
    今まで
    -1.02
    POSITIVE LOGITS
     also
    1.22
    ul
    1.22
    ha
    1.16
    u
    1.15
    us
    1.09
    le
    1.08
    k
    1.07
    ss
    1.06
    ga
    1.05
    ura
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.