© 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. 10-GEMMASCOPE-RES-131K
    7. 21904
    Prev
    Next
    INDEX
    Explanations

    mass events

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

    This neuron detects occurrences of the adjective “mass” when it modifies a following noun (e.g. “mass arrests,” “mass graves,” “mass casualty,” 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_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
    GEBUR
    -1.47
    ????????
    -1.46
    ?????
    -1.45
     cerrada
    -1.41
     людини
    -1.40
    ??????
    -1.39
     lámparas
    -1.39
    erdings
    -1.37
     kwiet
    -1.36
    ??"
    -1.36
    POSITIVE LOGITS
     of
    1.59
     不要
    1.41
    綃
    1.26
    unggulan
    1.23
    Всем
    1.21
     mempengaruhi
    1.20
     pamamagitan
    1.20
     From
    1.18
    Jetzt
    1.17
    只能
    1.16
    Activations Density 0.028%

    No Known Activations