© 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. 107379
    Prev
    Next
    INDEX
    Explanations

    semantic limits

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

    This neuron fires strongly on tokens that are names or labels of technical frameworks, libraries, or schema (e.g. “Semantic UI,” “JSON Schema,” “limits”).

    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
    illite
    -0.82
    ervi
    -0.77
     evento
    -0.76
     ecles
    -0.75
    closures
    -0.75
     hike
    -0.75
     ré
    -0.75
    setNome
    -0.75
     urbanas
    -0.75
     patate
    -0.75
    POSITIVE LOGITS
    </em>
    0.81
    essentiel
    0.79
     italiani
    0.79
     एप
    0.77
     relatório
    0.77
     geprek
    0.77
    </
    0.75
    rold
    0.75
    fra
    0.74
     instead
    0.74
    Activations Density 0.001%

    No Known Activations