© 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. 79991
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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
     Daarom
    -0.99
     velocidades
    -0.96
     Atenas
    -0.93
     Mereka
    -0.92
    ぜひ
    -0.90
    彼らは
    -0.90
     memasak
    -0.89
    müş
    -0.88
     joten
    -0.88
     donc
    -0.87
    POSITIVE LOGITS
     then
    1.55
     hoping
    1.23
     anschließend
    1.15
    เพื่อ
    1.10
    Result
    1.09
     Result
    1.09
     risposta
    1.09
     soon
    1.06
     to
    1.05
    すると
    1.05
    Activations Density 0.024%

    No Known Activations