© 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. 130272
    Prev
    Next
    INDEX
    Explanations

    structure of

    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
    </i>
    -1.93
    戋
    -1.46
    usions
    -1.39
    haviours
    -1.38
    ープン
    -1.38
    朥
    -1.37
    zzie
    -1.34
    我们
    -1.31
    %%%%
    -1.31
    齜
    -1.30
    POSITIVE LOGITS
     and
    1.57
    \
    1.52
    j
    1.39
     also
    1.38
     like
    1.34
     so
    1.34
    נם
    1.31
     first
    1.28
     actually
    1.26
     AND
    1.20
    Activations Density 0.091%

    No Known Activations