© 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. 72936
    Prev
    Next
    INDEX
    Explanations

    specific entities introduced by this

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

    The neuron strongly responds to self-referential demonstrative language—especially the word “this.”

    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
     trecut
    -1.55
    stricken
    -1.50
    ➆
    -1.48
     and
    -1.45
    轱
    -1.39
    ܃
    -1.38
    thodoxy
    -1.36
    pady
    -1.34
    いしい
    -1.34
    Londres
    -1.34
    POSITIVE LOGITS
    ↵
    2.09
     –
    1.55
     already
    1.52
     уже
    1.48
     know
    1.36
    t
    1.36
    to
    1.35
    することが
    1.34
    is
    1.31
     представляет
    1.30
    Activations Density 0.061%

    No Known Activations