© 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. 85048
    Prev
    Next
    INDEX
    Explanations

    potential to

    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
     about
    -1.57
    Toeschouwers
    -1.56
    ㆆ
    -1.48
    ”),
    -1.48
    izados
    -1.48
    かは
    -1.45
     on
    -1.43
    🥙
    -1.43
    🧆
    -1.42
     sedia
    -1.40
    POSITIVE LOGITS
     be
    1.59
    剮
    1.52
    ཋ
    1.47
    īgs
    1.44
    sukienka
    1.44
    ᆼ
    1.44
    </h4>
    1.43
    蛧
    1.42
    biendo
    1.42
     потому
    1.41
    Activations Density 0.019%

    No Known Activations