© 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. 75315
    Prev
    Next
    INDEX
    Explanations

    loop 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
    parka
    -1.37
    pueblo
    -1.36
     cordón
    -1.33
    בעת
    -1.30
    alakip
    -1.29
     cojín
    -1.28
     rompecabezas
    -1.28
     rése
    -1.27
     emplois
    -1.25
     bautizo
    -1.24
    POSITIVE LOGITS
     is
    1.41
    of
    1.30
    r
    1.30
    les
    1.30
    p
    1.28
     *
    1.27
    so
    1.25
    <h3>
    1.25
     with
    1.24
    no
    1.23
    Activations Density 0.003%

    No Known Activations