© 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. 54348
    Prev
    Next
    INDEX
    Explanations

    month and date

    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
    乸
    -2.69
    liebte
    -2.36
     работают
    -2.36
    __':
    -2.34
    ཥ
    -2.34
     начинают
    -2.27
    ’;
    -2.23
     každý
    -2.22
    zuführen
    -2.20
     był
    -2.19
    POSITIVE LOGITS
    \
    2.91
     AND
    2.63
    le
    2.59
    en
    2.48
    我们的
    2.33
     September
    2.30
    (
    2.30
     arduous
    2.28
     использование
    2.27
    al
    2.22
    Activations Density 0.031%

    No Known Activations