© 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. 85222
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    The neuron fires on capitalized proper names and other named-entity tokens.

    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
     this
    -1.66
     tersebut
    -1.41
     these
    -1.38
     decreased
    -1.34
    Nirvana
    -1.30
     簡
    -1.30
     jepang
    -1.29
    勿論
    -1.29
     combined
    -1.28
    Decrease
    -1.28
    POSITIVE LOGITS
    䜣
    1.55
     who
    1.51
     свои
    1.34
    //{
    1.34
    ownload
    1.30
     فإن
    1.29
    TagNumber
    1.25
    蠵
    1.25
     "..\..\
    1.24
     to
    1.23
    Activations Density 0.045%

    No Known Activations