© 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. 28476
    Prev
    Next
    INDEX
    Explanations

    do anything to get

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

    The neuron specifically fires on the indefinite pronoun “anything.”

    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
     instead
    -1.16
    kurtka
    -1.13
    卌
    -1.08
    贗
    -1.05
    всегда
    -1.02
    總是
    -1.01
    
    -1.01
    сього
    -1.00
     disminución
    -1.00
    的時間
    -1.00
    POSITIVE LOGITS
     to
    1.95
     including
    1.27
     get
    1.24
     protect
    1.23
     cualquier
    1.08
    elif
    1.06
     termasuk
    1.05
    เพื่อ
    1.05
    including
    1.02
     einschließlich
    1.02
    Activations Density 0.022%

    No Known Activations