© 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. 103295
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and metadata

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

    The neuron fires on tokens that occur in boilerplate or metadata sections (e.g. copyright headers, template comments, infobox labels, URLs/emails).

    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
     increased
    -1.00
     more
    -1.00
     even
    -0.97
     most
    -0.94
    cznym
    -0.93
     fairly
    -0.93
     or
    -0.92
     great
    -0.91
     changes
    -0.91
     surprisingly
    -0.90
    POSITIVE LOGITS
    geladen
    1.05
    Tamanho
    1.03
     SIZE
    0.98
    濆
    0.97
     témoin
    0.93
    tamanho
    0.92
    鲫
    0.92
     estructuras
    0.91
     tamanho
    0.91
    卺
    0.91
    Activations Density 0.000%

    No Known Activations