© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81059
    Prev
    Next
    INDEX
    Explanations

    say the least

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

    This neuron fires on the colloquial intensifier phrase “to say the least.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ayet
    -0.82
    parseColor
    -0.80
     プレミアム
    -0.79
     specialty
    -0.79
     signify
    -0.79
    جعل
    -0.78
     unangemessene
    -0.77
     スタジオ
    -0.77
     하는
    -0.76
    不断
    -0.75
    POSITIVE LOGITS
     mildly
    1.27
     at
    0.93
    voja
    0.93
    Mild
    0.92
     understatement
    0.89
     mild
    0.85
     Mild
    0.83
    bumptech
    0.82
    Bitpie
    0.81
     the
    0.81
    Activations Density 0.003%

    No Known Activations