© 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. 12396
    Prev
    Next
    INDEX
    Explanations

    statistical tests and analysis

    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
    ?
    -1.14
     complica
    -1.08
     conforme
    -1.05
     albu
    -1.05
     École
    -1.04
     favorita
    -1.03
    :"-"`
    -1.02
     imposto
    -1.02
    ounces
    -1.02
     Cerca
    -1.02
    POSITIVE LOGITS
     följande
    1.33
     odpo
    1.20
     for
    1.16
     lätt
    1.16
     какъ
    1.15
    ってました
    1.14
    Evet
    1.14
     Наталья
    1.13
    Abraço
    1.12
     Татьяна
    1.12
    Activations Density 0.018%

    No Known Activations