© 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. 10-GEMMASCOPE-RES-131K
    4. 39246
    Prev
    Next
    INDEX
    Explanations

    for example

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

    The neuron strongly responds to technical or domain-specific content words (e.g. nouns and verbs commonly found in manuals or formal process descriptions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     from
    -2.92
     by
    -2.28
     like
    -2.27
     through
    -2.08
     which
    -2.08
     one
    -2.05
     before
    -1.96
     so
    -1.94
     every
    -1.91
     during
    -1.91
    POSITIVE LOGITS
    ofing
    1.80
    
    1.68
    铙
    1.66
     disponibilités
    1.63
     are
    1.62
    jeni
    1.59
     musul
    1.59
    ፁ
    1.58
     magnificent
    1.58
    artment
    1.57
    Activations Density 0.256%

    No Known Activations