© 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. 60347
    Prev
    Next
    INDEX
    Explanations

    predicted outcomes and likelihoods

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

    This neuron specializes in spotting idiomatic multi-word phrases that combine a verb or adjective with a particle/preposition and a determiner—e.g. “sewn up,” “looked upon as a,” or “as big of favorites.”

    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
     impré
    -0.86
    西装
    -0.84
     relev
    -0.78
    Pantalla
    -0.75
    لیس
    -0.74
    gany
    -0.74
    efic
    -0.73
    Oft
    -0.73
    접
    -0.73
     metic
    -0.73
    POSITIVE LOGITS
     certainty
    2.19
     assured
    2.06
     lock
    1.99
     sure
    1.98
     guaranteed
    1.97
     slam
    1.81
     locks
    1.79
     shoe
    1.62
    assured
    1.59
    certainty
    1.53
    Activations Density 0.028%

    No Known Activations