© 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. 105822
    Prev
    Next
    INDEX
    Explanations

    starting or engaging in activities

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

    The neuron strongly activates on present‐participle (“‐ing”) verb forms—i.e. verbs in their gerund or progressive form.

    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
     if
    -1.72
    もう一度
    -1.45
     another
    -1.45
     one
    -1.35
     hermanas
    -1.30
     maritime
    -1.28
     homepage
    -1.26
     acaba
    -1.25
     signage
    -1.24
     internationale
    -1.23
    POSITIVE LOGITS
    </h5>
    1.70
     minuta
    1.39
     increasingly
    1.25
    </h3>
    1.21
    });
    1.20
    Læs
    1.18
    mills
    1.16
    ölcs
    1.15
     alumínio
    1.14
    يتها
    1.13
    Activations Density 0.079%

    No Known Activations