© 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. 59389
    Prev
    Next
    INDEX
    Explanations

    subdivision, record, career, people, discrete

    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
     your
    -1.98
     who
    -1.77
     our
    -1.59
     if
    -1.55
     their
    -1.52
    3
    -1.46
     each
    -1.42
     my
    -1.40
     you
    -1.40
    ?
    -1.36
    POSITIVE LOGITS
     pantalón
    1.63
     لكن
    1.61
    tismo
    1.41
     iaitu
    1.38
    ebaran
    1.37
     Ceinture
    1.35
     guantes
    1.34
     cinturón
    1.32
     elevador
    1.31
     Akismet
    1.30
    Activations Density 0.055%

    No Known Activations