© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    things beyond control

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

    The neuron fires on words and phrases expressing lack of control or inability to affect something.

    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
     powinno
    -1.03
     позволит
    -0.95
     hadn
    -0.89
     ioe
    -0.88
     frequentemente
    -0.88
    cass
    -0.87
    ]+$
    -0.86
     hau
    -0.85
     bụ
    -0.84
     vēl
    -0.84
    POSITIVE LOGITS
     but
    1.36
     cannot
    1.17
     BUT
    1.13
     невозможно
    1.06
    There
    1.02
    无法
    1.00
     there
    0.98
     unfortunately
    0.97
    However
    0.96
    Cannot
    0.96
    Activations Density 0.042%

    No Known Activations