© 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. 118743
    Prev
    Next
    INDEX
    Explanations

    districts or geography

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

    The neuron fires on occurrences of proper names and titles—places, organizations, legal bodies, and other named entities.

    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
     lej
    -1.44
     Europas
    -1.20
     Mechanic
    -1.20
     绿
    -1.15
    ſe
    -1.13
     ingredi
    -1.13
     Palest
    -1.13
     风格
    -1.11
    дѣ
    -1.11
     materi
    -1.10
    POSITIVE LOGITS
     it
    1.27
     who
    1.22
    5
    1.15
     @
    1.12
    It
    1.07
     to
    1.06
     I
    1.05
     name
    1.03
     chief
    1.03
     right
    1.02
    Activations Density 0.103%

    No Known Activations