© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87097
    Prev
    Next
    INDEX
    Explanations

    income and economic status

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

    The neuron flags occurrences of the financial term “income.”

    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
    and
    -2.41
    ll
    -2.27
    if
    -2.25
     the
    -2.23
    of
    -2.22
    in
    -2.09
    リンゴ
    -2.08
    }$
    -2.06
    );
    -2.05
    ":
    -1.96
    POSITIVE LOGITS
    ztes
    2.06
    ımız
    1.94
     Organizador
    1.85
     titolata
    1.82
     sadece
    1.82
    🕗
    1.72
     comunión
    1.68
    ↵↵
    1.64
     gatto
    1.63
    desliz
    1.63
    Activations Density 0.012%

    No Known Activations