© 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. 10-GEMMASCOPE-RES-131K
    4. 111115
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

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

    The neuron activates on tokens that are part of formal names or specialized technical terms—especially organizational, institutional, or domain‐specific nouns.

    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
     ベー
    -1.41
     exemplu
    -1.36
     ministres
    -1.34
     quartiers
    -1.33
     contenir
    -1.30
     détruire
    -1.29
     représentants
    -1.28
     planètes
    -1.26
    鉨
    -1.25
     armées
    -1.24
    POSITIVE LOGITS
     to
    2.17
     get
    1.73
     with
    1.32
     make
    1.29
     do
    1.29
    but
    1.28
    The
    1.25
     kanskje
    1.25
     nesten
    1.24
     A
    1.23
    Activations Density 0.387%

    No Known Activations