© 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. 73924
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming constructs

    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
    aben
    -0.95
     zdar
    -0.86
     geschenk
    -0.82
    ✻
    -0.82
    𝓖
    -0.82
     yüzük
    -0.81
    ApiRequest
    -0.81
     مكت
    -0.81
    ihnachts
    -0.80
     إعادة
    -0.79
    POSITIVE LOGITS
     while
    1.30
     with
    1.01
     by
    0.88
     concurrently
    0.88
     after
    0.85
     вони
    0.84
     which
    0.82
     subsequently
    0.81
    entuan
    0.79
     simultaneously
    0.79
    Activations Density 0.047%

    No Known Activations