© 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. 22-GEMMASCOPE-RES-131K
    4. 79643
    Prev
    Next
    INDEX
    Explanations

    freelance work and loans

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

    The neuron activates on metadata and byline terms that signal outside contributors or affiliations (e.g. “Contributing,” “Writer,” “Guest,” “affiliate,” “loan,” “contract,” “commission”).

    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
     texinfo
    -1.07
     criou
    -1.06
     entrou
    -1.06
     iria
    -1.05
     rę
    -1.05
     caiu
    -1.04
     esteve
    -1.02
     yyj
    -1.02
     escreveu
    -1.01
     estão
    -1.00
    POSITIVE LOGITS
     from
    2.30
     for
    1.38
     Fazit
    1.16
     From
    1.06
     particularly
    1.05
    }
    1.02
    سد
    0.99
    其他
    0.99
     since
    0.98
    特别
    0.98
    Activations Density 0.059%

    No Known Activations