© 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. 57536
    Prev
    Next
    INDEX
    Explanations

    criteria for

    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
    </strong>
    -1.83
    ቷ
    -1.54
     The
    -1.50
    やや
    -1.49
     omdat
    -1.46
    岂
    -1.46
    yaitu
    -1.44
     unforeseen
    -1.43
    ,
    -1.43
     أنها
    -1.42
    POSITIVE LOGITS
    嫆
    1.53
     godk
    1.52
    rógeno
    1.52
     anledning
    1.49
    .}(
    1.48
     kesel
    1.47
    癪
    1.41
     prêtres
    1.40
     作り方
    1.38
     familières
    1.37
    Activations Density 0.062%

    No Known Activations