© 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. 272
    Prev
    Next
    INDEX
    Explanations

    indeed or fact to add information

    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
    </tfoot>
    -1.84
    ༔
    -1.68
    cological
    -1.51
     РС
    -1.49
    ends
    -1.45
     there
    -1.45
    jected
    -1.44
     мамы
    -1.43
    ised
    -1.41
    then
    -1.40
    POSITIVE LOGITS
     The
    1.75
     häufigsten
    1.59
     ursprünglichen
    1.57
     our
    1.39
     früheren
    1.37
     даже
    1.37
     beliebtesten
    1.36
     jerry
    1.34
     schönsten
    1.34
     angegebenen
    1.34
    Activations Density 0.007%

    No Known Activations