© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59984
    Prev
    Next
    INDEX
    Explanations

    get to verb

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

    The neuron consistently fires on the token “to,” especially when it marks an infinitive or prepositional “to.”

    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
    \
    -2.50
    )$
    -2.47
    the
    -2.34
    4
    -2.33
    _
    -2.30
    (
    -2.30
    1
    -2.27
    U
    -2.23
    9
    -2.22
    </sub>
    -2.20
    POSITIVE LOGITS
     ſever
    2.30
    lewati
    2.25
     Perſ
    2.09
    ſu
    2.03
    Παρα
    2.02
    垆
    2.00
    Πηγή
    1.94
     แต่
    1.93
    también
    1.88
    jelaskan
    1.87
    Activations Density 0.003%

    No Known Activations