© 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. 73636
    Prev
    Next
    INDEX
    Explanations

    linking verb "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
     ܙ
    -3.56
    t
    -2.94
    雠
    -2.92
     we
    -2.84
    ଢ
    -2.78
    軚
    -2.70
    the
    -2.61
    嚶
    -2.58
    沨
    -2.55
    ଝ
    -2.53
    POSITIVE LOGITS
     There
    3.19
    There
    2.91
     これ
    2.73
     只
    2.59
    in
    2.38
     We
    2.34
     може
    2.34
     که
    2.28
    is
    2.28
            
    2.28
    Activations Density 0.058%

    No Known Activations