© 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. 13714
    Prev
    Next
    INDEX
    Explanations

    for or in or on or with followed by noun

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

    The neuron fires strongly on the preposition “for” when it introduces a purpose, target, or topic (as in “X for Y”) in titles or queries.

    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
    Its
    -2.02
    k
    -1.99
    its
    -1.99
    on
    -1.95
    把它
    -1.91
     delà
    -1.88
    id
    -1.74
    ang
    -1.74
    end
    -1.73
    ad
    -1.69
    POSITIVE LOGITS
     which
    2.03
     or
    1.80
     your
    1.73
     allowing
    1.70
    embley
    1.63
     using
    1.63
    aspectj
    1.63
    tedì
    1.59
     giving
    1.59
     with
    1.59
    Activations Density 0.016%

    No Known Activations