© 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. 128933
    Prev
    Next
    INDEX
    Explanations

    none is/are/was/were

    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
    宬
    -2.11
     גם
    -1.94
     também
    -1.85
     entanto
    -1.80
    also
    -1.77
    Также
    -1.72
     también
    -1.70
     này
    -1.63
     også
    -1.59
    viembre
    -1.56
    POSITIVE LOGITS
     estando
    1.66
     welchem
    1.63
     which
    1.59
    有三
    1.53
    когда
    1.50
    何时
    1.50
    lında
    1.48
     welchen
    1.41
    meeting
    1.41
     котором
    1.39
    Activations Density 0.024%

    No Known Activations