© 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. 10-GEMMASCOPE-RES-131K
    7. 127223
    Prev
    Next
    INDEX
    Explanations

    author: or address:

    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
    LookAnd
    -1.38
    ”،
    -1.31
    haël
    -1.29
     $^{
    -1.29
     skall
    -1.23
    ()){
    -1.23
    anthene
    -1.20
     betale
    -1.19
     on
    -1.19
    Ї
    -1.17
    POSITIVE LOGITS
    幸いです
    1.47
    those
    1.46
    both
    1.45
    that
    1.44
    :
    1.40
     acabó
    1.34
     barva
    1.33
    THIS
    1.27
     acoged
    1.27
     bílá
    1.27
    Activations Density 0.019%

    No Known Activations