© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111449
    Prev
    Next
    INDEX
    Explanations

    names of people and characters

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

    The neuron responds to proper names and other named entities (people’s names, show or film titles, etc.).

    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
    Galería
    -1.45
    Bullshit
    -1.42
    Clutch
    -1.42
    Producción
    -1.32
    Curiosidades
    -1.32
    Kilde
    -1.30
    Slik
    -1.30
    Geografía
    -1.30
    Chakra
    -1.27
    entait
    -1.27
    POSITIVE LOGITS
    “
    1.24
    :
    1.23
    ’
    1.20
     ObjectId
    1.17
    "
    1.15
     pertinentes
    1.15
    one
    1.15
    ‘
    1.14
     endereço
    1.13
     gelingt
    1.13
    Activations Density 0.085%

    No Known Activations