© 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. 850
    Prev
    Next
    INDEX
    Explanations

    crop or clip

    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
    ?”
    -1.85
    </h3>
    -1.54
    不敢
    -1.39
     nostre
    -1.39
    “,
    -1.35
     adesi
    -1.34
    ↵↵
    -1.34
     adesivo
    -1.30
     gav
    -1.30
    lahraga
    -1.30
    POSITIVE LOGITS
     the
    1.91
    '
    1.66
    -"
    1.59
     "
    1.58
    ="
    1.43
     to
    1.38
    uellement
    1.38
     وست
    1.37
    ERSON
    1.35
     shady
    1.33
    Activations Density 0.015%

    No Known Activations