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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102425
    Prev
    Next
    INDEX
    Explanations

    title of the entity

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

    The neuron is primarily activated by the preposition “of,” especially in “X of Y” or “owner of the”-type phrases.

    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
    </b>
    -1.73
    ).
    -1.63
    ;
    -1.57
    </strong>
    -1.56
    它
    -1.55
    ᾐ
    -1.53
     blivit
    -1.52
    tibles
    -1.52
    悄悄
    -1.51
     przede
    -1.51
    POSITIVE LOGITS
     there
    2.05
     of
    1.88
     wants
    1.87
     that
    1.77
     even
    1.58
     want
    1.53
     as
    1.53
     their
    1.48
     need
    1.48
     if
    1.42
    Activations Density 0.035%

    No Known Activations