© 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. 130315
    Prev
    Next
    INDEX
    Explanations

    things before conclusion or impact

    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
    updateOne
    -1.26
    Possibly
    -1.14
     (
    -1.10
    Only
    -1.05
     on
    -1.05
    warnai
    -1.04
     fré
    -1.03
     после
    -1.02
     glä
    -1.02
    Newly
    -1.02
    POSITIVE LOGITS
     it
    1.41
    </b>
    1.41
    了些
    1.34
    atchi
    1.33
     numele
    1.31
    就能
    1.29
    chtend
    1.28
     daher
    1.27
    了不少
    1.25
     dlatego
    1.23
    Activations Density 0.057%

    No Known Activations