© 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. 10-GEMMASCOPE-RES-131K
    7. 61051
    Prev
    Next
    INDEX
    Explanations

    is followed by yes

    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_10/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
     as
    -1.48
    Verwendung
    -1.24
    了下来
    -1.22
     siete
    -1.17
     onCancelled
    -1.17
    ↵↵
    -1.16
    ríguez
    -1.14
     for
    -1.13
    值的
    -1.13
    también
    -1.11
    POSITIVE LOGITS
     answer
    1.61
     that
    1.38
     answers
    1.38
    イエ
    1.23
    後は
    1.23
     this
    1.23
    Answer
    1.22
     yes
    1.22
    List
    1.17
    Color
    1.17
    Activations Density 0.086%

    No Known Activations