© 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. 70996
    Prev
    Next
    INDEX
    Explanations

    types of entities

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

    This neuron is primarily detecting the preposition “of.”

    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
    atellite
    -2.50
    縐
    -2.44
    ophageal
    -2.44
    ynthetic
    -2.30
    های
    -2.28
     youre
    -2.16
     if
    -2.16
    ſelves
    -2.13
    ious
    -2.02
    keleton
    -2.02
    POSITIVE LOGITS
     are
    2.69
    嘡
    2.58
     themselves
    2.55
    臵
    2.44
    亖
    2.30
    pecabe
    2.28
     to
    2.27
     meisten
    2.25
     erstes
    2.20
     erwähnten
    2.20
    Activations Density 2.689%

    No Known Activations