© 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. 99931
    Prev
    Next
    INDEX
    Explanations

    miss out on

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

    The neuron fires on occurrences of the phrase “miss out on,” i.e. that idiomatic construction.

    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
    }$
    -2.33
    久しぶり
    -2.05
     sicheren
    -1.86
     consultez
    -1.84
    有名な
    -1.76
    罠
    -1.71
     schnellen
    -1.70
     wydaje
    -1.70
    悧
    -1.68
     najczęściej
    -1.67
    POSITIVE LOGITS
    沨
    2.27
    between
    1.95
    :@"
    1.86
    轳
    1.84
    irled
    1.84
    潆
    1.82
    archiwizowane
    1.80
    辚
    1.77
    shafen
    1.75
    OUGH
    1.74
    Activations Density 0.004%

    No Known Activations