© 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. 10-GEMMASCOPE-RES-131K
    7. 13435
    Prev
    Next
    INDEX
    Explanations

    switch statements

    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
     multicolore
    -1.64
     GERMANY
    -1.52
     femininos
    -1.52
     unga
    -1.46
     zoude
    -1.46
     SEVENT
    -1.45
     pantalon
    -1.45
     aſ
    -1.43
     ananas
    -1.43
     alip
    -1.42
    POSITIVE LOGITS
     Some
    1.69
     different
    1.59
     From
    1.48
     those
    1.48
    Some
    1.46
     Некоторые
    1.45
     some
    1.44
     extremadamente
    1.41
     inmediatamente
    1.40
     ktoré
    1.39
    Activations Density 0.004%

    No Known Activations