© 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. 22-GEMMASCOPE-RES-131K
    7. 33841
    Prev
    Next
    INDEX
    Explanations

    Irish places

    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_22/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
     präsenti
    -1.48
     hombro
    -1.34
     gehörte
    -1.32
     veranstal
    -1.30
    чные
    -1.25
     which
    -1.23
     another
    -1.22
     silnik
    -1.22
     this
    -1.21
    mycin
    -1.21
    POSITIVE LOGITS
     Irish
    1.85
    Irish
    1.64
    Ireland
    1.60
     Ireland
    1.59
     irland
    1.38
     Dublin
    1.35
     Celtic
    1.34
     Gaelic
    1.34
     Galway
    1.33
    Dublin
    1.28
    Activations Density 0.059%

    No Known Activations