© 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. 54274
    Prev
    Next
    INDEX
    Explanations

    Polish and Turkish place names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is activated by and thus detects tokens containing non-ASCII letters or diacritic characters (e.g. Turkish or other accented letters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     directo
    -0.82
     ones
    -0.80
    ladelphia
    -0.75
    Fazit
    -0.74
     cil
    -0.73
     diman
    -0.73
     Sya
    -0.72
     misto
    -0.72
     этой
    -0.72
     stated
    -0.72
    POSITIVE LOGITS
     its
    1.26
     jego
    0.94
     njego
    0.93
     její
    0.86
     его
    0.85
     mine
    0.85
     її
    0.82
    ى
    0.82
     ее
    0.81
    cesi
    0.80
    Activations Density 0.016%

    No Known Activations