© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85497
    Prev
    Next
    INDEX
    Explanations

    Islam, TV, science

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

    The neuron primarily flags proper names and other named entities (e.g. people’s names, titles, festivals).

    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
    in
    -1.31
    ++];
    -1.26
    StatusCodes
    -1.24
    reated
    -1.23
     bahkan
    -1.20
    tioned
    -1.20
     setempat
    -1.18
    ..]
    -1.16
    .'
    -1.16
     voed
    -1.16
    POSITIVE LOGITS
     cannot
    1.24
    зий
    1.21
     manure
    1.16
    وق
    1.14
    ForEach
    1.13
    telijke
    1.13
    Gameplay
    1.10
     publicly
    1.07
     外観
    1.05
    Priest
    1.04
    Activations Density 0.019%

    No Known Activations