© 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. 92300
    Prev
    Next
    INDEX
    Explanations

    ging or ling suffixes

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

    The neuron detects the character sequence “ing” (including variations like “ingo”) embedded inside larger words.

    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
     radically
    -0.75
     enormously
    -0.73
    Caste
    -0.73
    друг
    -0.72
    لیسی
    -0.71
     ਕਿ
    -0.71
     immensely
    -0.70
    Demonstration
    -0.69
    ậm
    -0.69
     hustle
    -0.68
    POSITIVE LOGITS
    uyen
    0.85
    eles
    0.82
    els
    0.82
     Nationale
    0.81
    ierz
    0.79
    rij
    0.78
    ip
    0.78
    ė
    0.77
    eling
    0.76
    iber
    0.76
    Activations Density 0.021%

    No Known Activations