© 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. 22-GEMMASCOPE-RES-131K
    7. 25603
    Prev
    Next
    INDEX
    Explanations

    thrift, frugal, thrifty, or names starting with Thir

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

    The neuron activates on words related to frugality or thrift (e.g. thrift, thrifty, frugal).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    哢
    -2.59
    柺
    -2.39
    螣
    -2.17
    鷂
    -2.17
    葶
    -2.16
    罽
    -2.13
    澇
    -2.13
    苳
    -2.09
    コチラ
    -2.08
    aimeJ
    -2.08
    POSITIVE LOGITS
    .
    3.42
    ’
    3.31
    ",
    2.59
    ，
    2.50
    We
    2.38
    If
    2.25
    #
    2.23
    The
    2.22
    ',
    2.19
    $,
    2.19
    Activations Density 0.001%

    No Known Activations