© 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. 105808
    Prev
    Next
    INDEX
    Explanations

    code variable declarations

    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
     of
    -1.51
     vorher
    -1.40
     obfusc
    -1.33
     ihren
    -1.29
     ihrer
    -1.25
     vollen
    -1.25
    @[+][
    -1.21
     précisément
    -1.17
    те
    -1.14
     Again
    -1.13
    POSITIVE LOGITS
    觧
    1.58
     strade
    1.56
     Ć
    1.40
     Coruña
    1.38
     miliki
    1.38
     retrô
    1.37
     to
    1.35
     who
    1.34
     risposte
    1.34
     probleem
    1.32
    Activations Density 0.013%

    No Known Activations