© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49719
    Prev
    Next
    INDEX
    Explanations

    negative or conditional statements

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

    The neuron primarily detects the Chinese negation particle “不.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     not
    -1.16
    приєм
    -1.07
    事態
    -0.91
    wn
    -0.90
    を
    -0.89
    อยาก
    -0.89
    说
    -0.88
     juz
    -0.88
    実感
    -0.87
    mazaki
    -0.84
    POSITIVE LOGITS
     publiek
    1.06
    french
    0.99
     chociaż
    0.98
     ciepła
    0.98
    ziasztok
    0.97
     tijds
    0.96
     choć
    0.94
    aziland
    0.94
    gląda
    0.94
    beach
    0.93
    Activations Density 0.001%

    No Known Activations