© 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. 12239
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and international characters

    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
     in
    -2.38
     on
    -2.31
     by
    -2.05
     it
    -2.00
     there
    -1.88
     if
    -1.84
     while
    -1.78
     but
    -1.77
     and
    -1.66
     when
    -1.35
    POSITIVE LOGITS
     lesquels
    1.70
    ጺ
    1.63
    自分の
    1.59
    经过
    1.49
    自分
    1.48
    都可以
    1.47
     ۱۷
    1.46
     lesquelles
    1.44
    я
    1.44
    ఱ
    1.42
    Activations Density 0.002%

    No Known Activations