© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113003
    Prev
    Next
    INDEX
    Explanations

    proper nouns following certain syllables

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

    The neuron activates on capitalized named-entity tokens (proper names of people, places, or organizations).

    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
     you
    -1.50
    也想
    -1.47
     profundamente
    -1.29
     igualmente
    -1.27
    ⣞
    -1.25
     certamente
    -1.24
     espesor
    -1.24
     zelfs
    -1.24
    憋
    -1.24
     viviendas
    -1.23
    POSITIVE LOGITS
     and
    1.22
     as
    1.22
     can
    1.21
    ших
    1.15
     from
    1.13
     d
    1.13
    estero
    1.12
     because
    1.09
     like
    1.07
    LikeLiked
    1.06
    Activations Density 0.291%

    No Known Activations