© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95800
    Prev
    Next
    INDEX
    Explanations

    diet rules

    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
     will
    -1.34
    いつもの
    -1.30
     always
    -1.20
     your
    -1.20
    Напомним
    -1.16
    >,</
    -1.15
    我们
    -1.13
     всегда
    -1.13
     SizedBox
    -1.09
    いつも
    -1.07
    POSITIVE LOGITS
     I
    1.73
     my
    1.43
    apparently
    1.41
     according
    1.41
     apparently
    1.24
     reportedly
    1.23
     моего
    1.13
     literature
    1.11
     оказалось
    1.09
    described
    1.07
    Activations Density 0.065%

    No Known Activations