© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103098
    Prev
    Next
    INDEX
    Explanations

    Derry City and Strabane District

    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
    Not in Any Lists

    No Comments

    Negative Logits
    揍
    -0.73
     résoudre
    -0.73
    瞥
    -0.70
    zeb
    -0.70
    gv
    -0.70
     MILL
    -0.69
     tâ
    -0.69
     velho
    -0.69
    gp
    -0.69
    tw
    -0.69
    POSITIVE LOGITS
     Derry
    1.47
    presets
    0.85
     Troubles
    0.76
    liski
    0.75
     Aquinas
    0.74
    Der
    0.72
    Disc
    0.71
    ApJ
    0.71
     ATO
    0.71
    -</
    0.71
    Activations Density 0.031%

    No Known Activations