© 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. 119773
    Prev
    Next
    INDEX
    Explanations

    containers or storage

    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
     ...........
    -1.55
    蟊
    -1.47
    _____________
    -1.46
     gettyimages
    -1.45
     troupes
    -1.45
    Well
    -1.45
    it
    -1.45
    1
    -1.44
    ^{+}\
    -1.44
    itting
    -1.44
    POSITIVE LOGITS
    <bos>
    1.80
     former
    1.59
     они
    1.55
    })=
    1.48
    meability
    1.45
     With
    1.45
    }'.
    1.44
     cuando
    1.43
     когда
    1.42
     sartén
    1.42
    Activations Density 0.006%

    No Known Activations