© 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. 34-GEMMASCOPE-RES-131K
    7. 31587
    Prev
    Next
    INDEX
    Explanations

    location or characteristic of a place

    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
     ſeveral
    -1.05
     estancias
    -1.05
     thoſe
    -1.02
     that
    -0.98
     schnee
    -0.98
    ofing
    -0.96
    ्रीय
    -0.95
     those
    -0.95
     these
    -0.94
     każdy
    -0.93
    POSITIVE LOGITS
     a
    1.06
     experiencing
    1.05
     fertile
    0.94
     دارای
    0.86
     یکی
    0.85
    Exper
    0.83
     divided
    0.82
     gripped
    0.82
     spared
    0.82
    ция
    0.81
    Activations Density 0.056%

    No Known Activations