© 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. 66521
    Prev
    Next
    INDEX
    Explanations

    city districts and locations

    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
    鞴
    -2.11
     bianca
    -2.00
    Ꮉ
    -1.96
    the
    -1.95
    罨
    -1.82
     onor
    -1.80
    they
    -1.79
    涠
    -1.76
    
    -1.75
     Settembre
    -1.74
    POSITIVE LOGITS
    )
    2.38
    !
    2.05
    :
    1.95
     be
    1.77
     veinte
    1.73
     Город
    1.72
    i
    1.70
     squander
    1.67
    "
    1.66
     zwischen
    1.66
    Activations Density 0.010%

    No Known Activations