© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49253
    Prev
    Next
    INDEX
    Explanations

    events that happened before

    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_34/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
     after
    -1.62
     it
    -1.61
    because
    -1.34
    скажите
    -1.33
     después
    -1.32
     também
    -1.30
    after
    -1.30
     también
    -1.29
    '].
    -1.27
    €”
    -1.27
    POSITIVE LOGITS
     his
    1.35
    ,
    1.27
     alcune
    1.14
     parfums
    1.13
    ward
    1.10
     further
    1.10
     ESTABL
    1.06
     weeks
    1.06
     quelques
    1.05
     Rasen
    1.03
    Activations Density 0.054%

    No Known Activations