© 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. 60377
    Prev
    Next
    INDEX
    Explanations

    design and topic

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

    This neuron tracks how far into the document a token appears—later tokens yield higher activations.

    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
     čier
    -0.98
     москва
    -0.97
     Евгений
    -0.93
     mendengarkan
    -0.92
     obligaciones
    -0.90
    📐
    -0.89
     componentes
    -0.88
    tually
    -0.88
     cualidades
    -0.88
     BeautifulSoup
    -0.87
    POSITIVE LOGITS
     semblance
    0.84
     supports
    0.84
     worth
    0.81
     verdure
    0.80
    Dots
    0.79
    值得
    0.79
    Toaster
    0.79
     unanimous
    0.78
     presented
    0.77
     Modo
    0.77
    Activations Density 0.016%

    No Known Activations