© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9986
    Prev
    Next
    INDEX
    Explanations

    within, to, down 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
     of
    -2.06
     工房
    -1.49
    …”
    -1.49
     スケッチ
    -1.48
    omorphisms
    -1.46
    <bos>
    -1.45
    เรา
    -1.43
     большую
    -1.42
    otropy
    -1.41
    ?”
    -1.40
    POSITIVE LOGITS
    </b>
    1.68
     jedynie
    1.63
     recién
    1.53
     between
    1.50
     veränder
    1.48
     its
    1.48
     tatsäch
    1.48
     pensaba
    1.47
     rates
    1.45
     niezbęd
    1.45
    Activations Density 0.033%

    No Known Activations