© 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. 14940
    Prev
    Next
    INDEX
    Explanations

    endurance, completion, or continuation

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

    The neuron is firing on the phrasal-verb particle “out” (and its small pronoun object in “waiting it out”), i.e. it detects “out” when it functions as the verb’s particle indicating completion or duration.

    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
     Púb
    -1.98
    锲
    -1.82
    struzioni
    -1.74
     Emphasis
    -1.66
    他に
    -1.65
    Surprisingly
    -1.63
     >/
    -1.62
     تھے
    -1.59
    »،
    -1.55
     階段
    -1.55
    POSITIVE LOGITS
    鹛
    1.93
    ]}$
    1.74
     konnte
    1.71
    しているので
    1.70
     juſ
    1.68
     viſ
    1.65
    </i>
    1.65
    та
    1.61
    isait
    1.61
    ния
    1.59
    Activations Density 0.004%

    No Known Activations