© 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. 68952
    Prev
    Next
    INDEX
    Explanations

    dole out / shell out / hand out

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

    The neuron detects phrasal verbs that include the particle “out” (e.g. dole out, hand out, shell out, churn out), signaling the act of dispensing or producing something.

    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
     vstup
    -1.95
     Geruch
    -1.83
    渽
    -1.82
    睒
    -1.80
    )\}$
    -1.73
     rígido
    -1.73
    孖
    -1.72
    エロ
    -1.72
    話が
    -1.70
    crizione
    -1.69
    POSITIVE LOGITS
    for
    2.08
     was
    2.03
    at
    1.95
    ta
    1.92
    O
    1.88
    is
    1.84
     fungerer
    1.76
    as
    1.75
    nalité
    1.67
     has
    1.66
    Activations Density 0.004%

    No Known Activations