© 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. 956
    Prev
    Next
    INDEX
    Explanations

    although followed by verb

    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
     and
    -2.34
     is
    -2.03
     when
    -1.94
     if
    -1.94
    </i>
    -1.92
     because
    -1.91
     but
    -1.77
     even
    -1.65
     also
    -1.58
     как
    -1.54
    POSITIVE LOGITS
    eventually
    1.77
    still
    1.73
     berücksich
    1.71
     excelentes
    1.70
     jednej
    1.67
    actéristi
    1.60
     сделали
    1.59
    还是很
    1.59
     nadal
    1.58
     its
    1.56
    Activations Density 0.120%

    No Known Activations