© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72654
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    resave
    -1.02
    sproble
    -1.00
    //};
    -0.97
     唯美
    -0.96
    expiresIn
    -0.96
    Descripcion
    -0.95
    ченных
    -0.94
    kasten
    -0.93
    InstrumentedTest
    -0.93
    Stad
    -0.93
    POSITIVE LOGITS
     its
    1.21
    It
    1.09
     gjø
    1.02
     forsø
    1.02
     lichaam
    1.02
     påvir
    1.02
     外観
    0.99
     løs
    0.98
     how
    0.97
     required
    0.97
    Activations Density 0.003%

    No Known Activations