© 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. 98863
    Prev
    Next
    INDEX
    Explanations

    comparative or superlative evaluation

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

    The neuron fires strongly on verbs and related words that describe how a system or thing functions (e.g. “relies,” “builds,” “works,” “are both successful,” etc.).

    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
     ">=
    -1.03
    lgica
    -0.97
     contribué
    -0.97
    *****/
    -0.91
     roba
    -0.89
    írito
    -0.88
     masih
    -0.87
     sudah
    -0.86
     armas
    -0.85
    갖
    -0.84
    POSITIVE LOGITS
     best
    2.41
     better
    2.30
     mejor
    1.95
     лучше
    1.89
     najlepiej
    1.84
     happiest
    1.76
     happier
    1.64
    better
    1.64
     bäst
    1.62
    best
    1.59
    Activations Density 0.084%

    No Known Activations