© 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. 65644
    Prev
    Next
    INDEX
    Explanations

    document status or type

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

    The neuron fires on structured metadata fields—especially labels and their numeric values (e.g. “Individual paper/presentation (20-minute presentation)”, “ASCII text”, “Copyright Status: Not copyrighted in the United States,” etc.).

    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
    Ⓡ
    -1.21
     all
    -1.17
     and
    -1.12
     occafion
    -1.10
     hanggang
    -1.09
    
    -1.09
     I
    -1.08
    :')
    -1.05
    !?"
    -1.05
    usive
    -1.05
    POSITIVE LOGITS
    Soorten
    1.23
    €¢
    1.20
     facultad
    1.19
     preferências
    1.19
     relâche
    1.17
    توضیحات
    1.16
    Einstellungen
    1.15
     lección
    1.15
    معرفی
    1.14
    Zitat
    1.13
    Activations Density 0.077%

    No Known Activations