© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56745
    Prev
    Next
    INDEX
    Explanations

    village or town names

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    玦
    -0.85
     écout
    -0.85
    ⡟
    -0.84
    trash
    -0.83
     districts
    -0.83
     kya
    -0.82
     modificaciones
    -0.82
     décé
    -0.82
     basura
    -0.81
    ฒ
    -0.81
    POSITIVE LOGITS
     block
    1.19
     sub
    1.16
     gram
    1.02
     Revenue
    0.98
     revenue
    0.97
     Block
    0.94
     town
    0.91
     tal
    0.91
     Gram
    0.91
     constituency
    0.90
    Activations Density 0.061%

    No Known Activations