© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58775
    Prev
    Next
    INDEX
    Explanations

    version numbers and numeric comparisons

    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
     також
    -1.58
     भी
    -1.55
    なども
    -1.44
    possibly
    -1.39
     also
    -1.36
    perhaps
    -1.34
    overall
    -1.27
     също
    -1.26
    also
    -1.25
     потенциаль
    -1.22
    POSITIVE LOGITS
     that
    1.58
     vya
    1.40
     already
    1.38
    Already
    1.30
     increases
    1.30
     Uang
    1.30
    已經
    1.23
     would
    1.23
     bereits
    1.22
    ਸ਼
    1.21
    Activations Density 0.016%

    No Known Activations