© 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. 10-GEMMASCOPE-RES-131K
    7. 87362
    Prev
    Next
    INDEX
    Explanations

    retirement plans and savings

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

    The neuron is strongly activated by occurrences of the word “retirement.”

    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
    '
    -2.86
    畚
    -2.45
    2
    -2.36
    颪
    -2.31
    倥
    -2.30
     pernikahan
    -2.23
    ことを
    -2.22
     стал
    -2.19
    猻
    -2.17
    魮
    -2.13
    POSITIVE LOGITS
    姈
    3.67
    媗
    3.17
    that
    2.78
    .
    2.67
    ,”
    2.66
    脔
    2.56
     که
    2.44
    ྃ
    2.41
    }
    2.38
    ”،
    2.34
    Activations Density 0.002%

    No Known Activations