© 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. 22-GEMMASCOPE-RES-131K
    7. 95589
    Prev
    Next
    INDEX
    Explanations

    forest park

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

    The neuron fires on multi‐token proper names—people’s names, place names, species names, titles, etc.—i.e. 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_22/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
    levis
    -1.31
     siè
    -1.28
     kolejny
    -1.27
     envoyer
    -1.26
     disminuir
    -1.23
    posisi
    -1.23
    acce
    -1.23
     trabalha
    -1.21
     garantir
    -1.20
     calzado
    -1.16
    POSITIVE LOGITS
     as
    1.47
     on
    1.34
     (
    1.27
     is
    1.25
    y
    1.20
    p
    1.19
    n
    1.16
    al
    1.13
    v
    1.12
    z
    1.12
    Activations Density 0.023%

    No Known Activations