© 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. 8603
    Prev
    Next
    INDEX
    Explanations

    got to verb

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

    The neuron fires on “to + verb” infinitive constructions (e.g. “to make,” “to have,” “to sit”).

    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
    \\
    -1.37
    日閲覧
    -1.30
    _
    -1.26
    \
    -1.23
    虽说
    -1.23
        
    -1.15
    ),
    -1.13
    one
    -1.13
    end
    -1.12
     berättar
    -1.11
    POSITIVE LOGITS
    הגב
    1.43
     hemd
    1.39
    𝐙
    1.36
    闋
    1.35
     disfru
    1.35
    lıyor
    1.34
    vonne
    1.34
     klim
    1.33
     größe
    1.32
    muito
    1.31
    Activations Density 0.025%

    No Known Activations