© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63728
    Prev
    Next
    INDEX
    Explanations

    as

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

    The neuron is primarily detecting words that describe actions or processes (i.e. verbs, participles, and their accompanying adverbs/modifiers).

    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
    owel
    -0.95
     enví
    -0.93
     zaidi
    -0.93
    มากกว่า
    -0.93
    ائدة
    -0.92
    UVEN
    -0.91
    τών
    -0.91
    
    -0.91
     lleve
    -0.91
    Schul
    -0.90
    POSITIVE LOGITS
     as
    4.88
     nearly
    2.72
     quite
    2.50
    Nearly
    2.14
     Nearly
    2.03
    nearly
    2.03
    Quite
    1.81
    quite
    1.74
     Quite
    1.74
     so
    1.72
    Activations Density 0.057%

    No Known Activations