© 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. 1538
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by "is"

    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
     those
    -1.78
     any
    -1.77
     which
    -1.70
     the
    -1.63
     these
    -1.63
     you
    -1.63
    França
    -1.58
     such
    -1.54
     with
    -1.50
     its
    -1.40
    POSITIVE LOGITS
    (!__
    1.54
    ><
    1.50
     otras
    1.48
    </i>
    1.45
    ";
    1.42
    "));
    1.42
    %;
    
    1.35
    ("
    1.35
    ");
    1.34
    </td>
    1.33
    Activations Density 0.255%

    No Known Activations