© 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. 80901
    Prev
    Next
    INDEX
    Explanations

    internal control or standard

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

    This neuron fires strongly on the word “internal,” especially when used in contexts like “internal control.”

    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
    ーズ
    -0.65
     Horror
    -0.65
     owed
    -0.65
    tisk
    -0.64
     CC
    -0.64
     planetary
    -0.63
     propia
    -0.62
     biodiversity
    -0.62
     ABC
    -0.61
     FCC
    -0.61
    POSITIVE LOGITS
    disposed
    0.81
    vinner
    0.76
     Magellan
    0.69
    パック
    0.68
     воды
    0.68
    velle
    0.66
     Atlan
    0.66
     Sticker
    0.66
    といふ
    0.65
     capelli
    0.64
    Activations Density 0.079%

    No Known Activations