© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33265
    Prev
    Next
    INDEX
    Explanations

    Turkish and European company or place names

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

    The neuron is triggered by tokens that are parts of Turkish proper names (especially place names and family/organization names).

    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
     by
    -1.08
     jelasnya
    -1.01
    🪅
    -0.97
     several
    -0.96
     two
    -0.95
    たって
    -0.95
     noted
    -0.93
    していますが
    -0.92
    そうですが
    -0.91
     including
    -0.91
    POSITIVE LOGITS
     Hinblick
    1.11
    UseVisualStyle
    1.09
     jakiś
    0.99
     rues
    0.98
    AddWithValue
    0.98
    EZ
    0.98
    upported
    0.98
    ዑ
    0.97
     zubere
    0.97
    EI
    0.96
    Activations Density 0.002%

    No Known Activations