© 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. 10-GEMMASCOPE-RES-131K
    7. 65523
    Prev
    Next
    INDEX
    Explanations

    evaluate, assess, explore, identify

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

    The neuron fires most strongly on verbs that denote concrete actions or processes (e.g. detect, prevent, procure, find, assess, uncover, explore).

    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
     you
    -1.75
    tedì
    -1.69
     karena
    -1.63
    &
    -1.53
    ająca
    -1.52
     çünkü
    -1.50
     большой
    -1.48
     proveniente
    -1.48
     unangemessene
    -1.47
     we
    -1.45
    POSITIVE LOGITS
    mohon
    1.54
     信息
    1.54
    咘
    1.48
    Chloroform
    1.48
    枷
    1.45
    Chiara
    1.44
    ꧁
    1.44
     资源
    1.43
     a
    1.40
     čist
    1.40
    Activations Density 0.057%

    No Known Activations