© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9300
    Prev
    Next
    INDEX
    Explanations

    company or product names

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

    The neuron strongly activates on well‐known product, service, or company names (brand/trademark mentions).

    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
    ."
    -1.31
    This
    -1.28
     iconic
    -1.25
     Sortiment
    -1.23
     gezeigt
    -1.20
    広い
    -1.20
    An
    -1.16
     gefördert
    -1.16
    尤其
    -1.15
     pertanyaan
    -1.13
    POSITIVE LOGITS
     or
    1.31
    之类的
    1.21
    asties
    1.18
    erdings
    1.18
     systeem
    1.16
    vább
    1.16
     ponts
    1.16
    ℅
    1.15
    €/
    1.15
     etc
    1.12
    Activations Density 0.074%

    No Known Activations