© 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. 72545
    Prev
    Next
    INDEX
    Explanations

    out of

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

    The neuron strongly activates on the phrase “out of,” i.e. prepositional constructions expressing removal or exclusion (e.g. “pushed out of,” “squeezed out of,” “blown out of”).

    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
     these
    -2.17
     to
    -2.13
     both
    -2.03
     those
    -2.00
     you
    -1.97
     that
    -1.88
     such
    -1.75
     or
    -1.63
     people
    -1.63
    (
    -1.59
    POSITIVE LOGITS
    Defence
    1.62
     vif
    1.53
    龘
    1.52
    然后
    1.51
     ansi
    1.49
     jonka
    1.48
     fei
    1.48
    鐽
    1.48
     mame
    1.48
     icônes
    1.48
    Activations Density 0.022%

    No Known Activations