© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67078
    Prev
    Next
    INDEX
    Explanations

    their or These

    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
    ),
    -1.34
    4
    -1.29
    ++;
    -1.29
     dicendo
    -1.28
    ())
    -1.28
    其他
    -1.27
     decorazione
    -1.26
     type
    -1.26
    مزید
    -1.25
     into
    -1.23
    POSITIVE LOGITS
     they
    2.25
    Their
    2.20
     Their
    2.08
     their
    2.00
    their
    1.90
    他们
    1.70
     THEIR
    1.66
     They
    1.65
    <bos>
    1.62
     jejich
    1.57
    Activations Density 0.083%

    No Known Activations