© 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. 111130
    Prev
    Next
    INDEX
    Explanations

    phrases with "out there"

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

    The neuron is strongly triggered by the little “verb‐particles” or prepositions that go with verbs in phrasal‐verb constructions (e.g. “put out,” “go after,” “look at,” “got rid of,” etc.).

    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
    </td>
    -1.92
     this
    -1.40
    3
    -1.34
    [
    -1.33
    				
    -1.31
    (
    -1.28
    {
    -1.26
    setcounter
    -1.23
     صفحات
    -1.23
     که
    -1.21
    POSITIVE LOGITS
    .”
    1.38
     рестай
    1.34
    淶
    1.28
    necked
    1.25
     occuper
    1.23
     milyen
    1.22
    嫪
    1.22
     связанные
    1.21
    और
    1.20
    aito
    1.20
    Activations Density 0.173%

    No Known Activations