© 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. 113720
    Prev
    Next
    INDEX
    Explanations

    for

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

    The neuron consistently activates on instances of the preposition “for.”

    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
     the
    -2.23
     our
    -2.05
     your
    -1.97
     från
    -1.88
    PTEMBER
    -1.84
     atriz
    -1.80
    ON
    -1.80
    PARATION
    -1.80
    y
    -1.77
    栻
    -1.77
    POSITIVE LOGITS
    日発売
    1.96
    .
    1.84
     nachdem
    1.75
    '
    1.66
    <bos>
    1.66
    ronesia
    1.63
    anical
    1.59
    icago
    1.59
     _
    1.59
    essoal
    1.56
    Activations Density 0.133%

    No Known Activations