© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129884
    Prev
    Next
    INDEX
    Explanations

    numbers and gender counts

    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
     to
    -2.55
     you
    -2.00
    on
    -1.63
     while
    -1.58
     as
    -1.47
    to
    -1.46
    len
    -1.45
    nyard
    -1.43
    ct
    -1.40
    cn
    -1.33
    POSITIVE LOGITS
     églises
    1.55
     sociétés
    1.47
     évaluations
    1.38
     入っ
    1.38
     collè
    1.38
     disponibilités
    1.37
     échanti
    1.36
     preuves
    1.35
     véritables
    1.35
     voitures
    1.33
    Activations Density 0.065%

    No Known Activations