© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85772
    Prev
    Next
    INDEX
    Explanations

    appropriation acts and budget requests

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

    This neuron detects variants of the word “appropriate” (and its noun form “appropriation”), including usages in funding contexts (e.g. government appropriations, requests) and related senses (e.g. misappropriation, co-opt).

    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
    or
    -3.17
    ка
    -2.77
    al
    -2.72
    ent
    -2.64
    time
    -2.59
    be
    -2.42
    on
    -2.41
    \
    -2.41
    with
    -2.41
    can
    -2.36
    POSITIVE LOGITS
    ญี่ป
    2.47
    枓
    2.30
     biela
    2.28
    blusa
    2.23
    焌
    2.14
    zja
    2.08
    灵气
    2.03
    忆
    2.03
    韡
    2.02
    なんですが
    2.00
    Activations Density 0.004%

    No Known Activations