© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    property description prefixes

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

    This neuron detects the presence of structured listing or advertisement language—especially numeric details and listing-style tokens (e.g. “with,” numbers, headings) typical of property, job, or item ads.

    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
     their
    -1.36
     by
    -1.30
     desmotiv
    -1.18
    kenzo
    -1.15
     estreia
    -1.12
     even
    -1.09
     республики
    -1.09
    ₇
    -1.06
    satunya
    -1.05
    levis
    -1.05
    POSITIVE LOGITS
     сериал
    1.13
    isks
    1.09
    れたら
    1.05
     roupas
    1.04
    сить
    1.04
    soap
    1.03
    if
    1.02
    ፫
    1.02
    hift
    1.01
     antigos
    1.00
    Activations Density 0.002%

    No Known Activations