© 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. 70942
    Prev
    Next
    INDEX
    Explanations

    is not working

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

    The neuron fires on the pronoun “it” when used as the subject of a clause (e.g. “it goes…,” “it is…,” “it is not working…”).

    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
    formatics
    -1.65
    calça
    -1.57
     limone
    -1.54
    ین
    -1.47
     刘
    -1.46
     gambe
    -1.42
    riezmann
    -1.40
    osing
    -1.39
     miele
    -1.39
     milano
    -1.38
    POSITIVE LOGITS
     стороны
    1.34
     чтобы
    1.33
    section
    1.33
     ayudó
    1.32
     a
    1.32
     sucedió
    1.32
    Menurut
    1.30
    漕
    1.30
    ühnen
    1.28
     suavemente
    1.28
    Activations Density 0.164%

    No Known Activations